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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्रमण
    -0.07
     preg
    -0.07
    onavir
    -0.07
    ToSelector
    -0.07
     acl
    -0.07
    akhir
    -0.06
     Kanye
    -0.06
     Ζ
    -0.06
     titanium
    -0.06
    йте
    -0.06
    POSITIVE LOGITS
     forests
    0.07
     role
    0.06
    According
    0.06
    [String
    0.06
    _cycles
    0.06
    итай
    0.06
     fishing
    0.06
    03
    0.06
     Mostly
    0.06
    Neighbor
    0.06
    Act Density 0.001%

    No Known Activations