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

    Neuronpedia

    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     radi
    -0.06
     north
    -0.06
     включ
    -0.06
     fascism
    -0.06
     xAxis
    -0.06
     returnType
    -0.06
     SETUP
    -0.06
     tet
    -0.06
    ([{
    -0.06
     nationalism
    -0.06
    POSITIVE LOGITS
     जब
    0.07
    licate
    0.07
     UT
    0.07
    atching
    0.07
    argout
    0.07
    joy
    0.07
    ⟩
    0.07
    bral
    0.06
    callback
    0.06
    .moves
    0.06
    Act Density 0.000%

    No Known Activations