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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurement tokens (especially floating‐point values and statistics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wizards
    -0.06
    ISING
    -0.06
    gets
    -0.06
    relu
    -0.06
     semble
    -0.06
    datepicker
    -0.06
    )L
    -0.06
    乂
    -0.06
    균
    -0.06
    \t
    -0.06
    POSITIVE LOGITS
     neo
    0.06
     Nature
    0.06
     Atmospheric
    0.06
    /or
    0.06
     spou
    0.06
     Andrew
    0.06
     στις
    0.06
     dignity
    0.06
     země
    0.06
    	ev
    0.06
    Act Density 0.001%

    No Known Activations