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

    Neuronpedia

    INDEX
    Explanations

    'll

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    眺
    -0.08
     upon
    -0.07
    .private
    -0.07
    .amazon
    -0.07
    帔
    -0.07
    诩
    -0.07
    -away
    -0.07
     erste
    -0.06
    פרק
    -0.06
    (if
    -0.06
    POSITIVE LOGITS
    Shares
    0.07
     losses
    0.07
    laughter
    0.07
    Lifetime
    0.07
    GetValue
    0.07
    ／
    0.07
     vocab
    0.07
    totals
    0.07
     strengths
    0.07
    的良好
    0.06
    Act Density 0.000%

    No Known Activations