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

    Neuronpedia

    INDEX
    Explanations

    Code & general english

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TIM
    -0.07
    須
    -0.07
     decade
    -0.07
     Wyn
    -0.07
     Theodore
    -0.06
     ethos
    -0.06
     presents
    -0.06
     precondition
    -0.06
    _RECV
    -0.06
    _superuser
    -0.06
    POSITIVE LOGITS
    POP
    0.07
     damp
    0.06
    rop
    0.06
    Classic
    0.06
     ně
    0.06
    qualified
    0.06
     Symbol
    0.06
    著
    0.06
    گران
    0.06
     nắng
    0.06
    Act Density 0.000%

    No Known Activations