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

    Neuronpedia

    INDEX
    Explanations

    github repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	o
    -0.07
    (static
    -0.07
    (U
    -0.07
     amused
    -0.06
     eased
    -0.06
     STD
    -0.06
    =color
    -0.06
     ml
    -0.06
    Parsed
    -0.06
    mits
    -0.06
    POSITIVE LOGITS
    ONGLONG
    0.07
    му
    0.07
     Paolo
    0.06
     Australians
    0.06
     Tuy
    0.06
     peer
    0.06
    폭
    0.06
    литель
    0.06
    /pm
    0.06
    JSONException
    0.06
    Act Density 0.006%

    No Known Activations