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

    Neuronpedia

    INDEX
    Explanations

    char

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corona
    -0.08
     fid
    -0.07
    ovu
    -0.07
     flow
    -0.07
     ansch
    -0.07
    _PB
    -0.06
     vertically
    -0.06
     Plato
    -0.06
     जर
    -0.06
    olis
    -0.06
    POSITIVE LOGITS
    zení
    0.06
    'є
    0.06
    conversation
    0.06
    報
    0.06
    ％
    0.06
    %");↵
    0.06
    .D
    0.06
    .Dis
    0.06
    .Pr
    0.06
    ;")↵
    0.06
    Act Density 0.001%

    No Known Activations