Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical support questions

    np_max-act · gemini-2.0-flash

    technical issues or errors related to computer programming and software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on numeric tokens containing a decimal point (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     AIDS
    -0.07
    .JWT
    -0.07
    	then
    -0.07
    elm
    -0.07
    ındır
    -0.06
     encore
    -0.06
     zlat
    -0.06
    やる
    -0.06
     Του
    -0.06
    .thumbnail
    -0.06
    POSITIVE LOGITS
     Roo
    0.07
     setups
    0.06
    _sin
    0.06
     steals
    0.06
     stressing
    0.06
    '];
    0.06
     Solutions
    0.06
     Handy
    0.06
    COM
    0.06
    textBox
    0.06
    Act Density 0.074%

    No Known Activations