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

    Neuronpedia

    INDEX
    Explanations

    References with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tune
    -0.07
    woo
    -0.06
    Rendering
    -0.06
    чний
    -0.06
     Friendship
    -0.06
     Though
    -0.06
    RAFT
    -0.06
     washed
    -0.06
     porque
    -0.06
     Quiz
    -0.06
    POSITIVE LOGITS
     utilizado
    0.07
     NZ
    0.07
     Bride
    0.06
    ापस
    0.06
     entrepreneurs
    0.06
     página
    0.06
    .precision
    0.06
    _forms
    0.06
    \Service
    0.06
    _CPP
    0.06
    Act Density 0.006%

    No Known Activations