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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dec
    -0.07
     decorating
    -0.06
    UILD
    -0.06
     lava
    -0.06
     sagen
    -0.06
     meaningful
    -0.06
    时候
    -0.06
    616
    -0.06
     SOCIAL
    -0.06
     supermarket
    -0.06
    POSITIVE LOGITS
    conduct
    0.08
    ру
    0.07
     urč
    0.06
    arih
    0.06
    orm
    0.06
    σφα
    0.06
     معن
    0.06
    miner
    0.06
    parseFloat
    0.06
     capacit
    0.06
    Act Density 0.024%

    No Known Activations