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

    Neuronpedia

    INDEX
    Explanations

    punctuation/special characters

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Chooser
    -0.08
    }'.
    -0.08
     Wake
    -0.07
     {}:
    -0.07
    รด
    -0.06
    互
    -0.06
    ">%
    -0.06
    phetamine
    -0.06
     gerekir
    -0.06
    	nodes
    -0.06
    POSITIVE LOGITS
     juvenile
    0.07
    veřej
    0.06
     redesigned
    0.06
    -expand
    0.06
     ul
    0.06
     Knowing
    0.06
    bam
    0.06
    'r
    0.06
    .selected
    0.06
    ippers
    0.06
    Act Density 0.087%

    No Known Activations