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

    Neuronpedia

    INDEX
    Explanations

    colon symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estr
    -0.08
    ARB
    -0.07
     коміс
    -0.07
     ISIL
    -0.07
    _dep
    -0.06
     indx
    -0.06
     PROP
    -0.06
    852
    -0.06
     neglig
    -0.06
     permits
    -0.06
    POSITIVE LOGITS
    ForRow
    0.07
    anic
    0.06
    =Math
    0.06
    年度
    0.06
    Spy
    0.06
    ヶ月
    0.06
    ryfall
    0.06
     Од
    0.06
    :
    0.06
    ør
    0.06
    Act Density 0.089%

    No Known Activations