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

    Neuronpedia

    INDEX
    Explanations

    .com .org

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ле
    0.84
     llamadas
    0.84
    тным
    0.83
    interacting
    0.81
     такими
    0.79
    attoo
    0.79
     chiam
    0.79
     affid
    0.77
    anganese
    0.76
    olly
    0.75
    POSITIVE LOGITS
    posts
    0.83
    =/
    0.80
    ="#
    0.80
    wald
    0.78
     判断
    0.75
    ="/
    0.73
    说明
    0.72
    valu
    0.72
     />,
    0.72
     trakcie
    0.72
    Act Density 0.005%

    No Known Activations