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

    Neuronpedia

    INDEX
    Explanations

    currency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     portray
    -0.07
     Own
    -0.07
     tanks
    -0.07
     THR
    -0.06
     Order
    -0.06
     CharSequence
    -0.06
     butt
    -0.06
    xDA
    -0.06
    кую
    -0.06
    _ZONE
    -0.06
    POSITIVE LOGITS
    rač
    0.07
    _twitter
    0.07
     pracy
    0.07
    ublik
    0.07
    _FieldOffsetTable
    0.06
    \\
    0.06
     respons
    0.06
     Ravens
    0.06
     Crafting
    0.06
    %^
    0.06
    Act Density 0.038%

    No Known Activations