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

    Neuronpedia

    INDEX
    Explanations

    slash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monkey
    -0.08
    .—
    -0.08
    "She
    -0.07
     Exercise
    -0.07
    —with
    -0.07
    exterity
    -0.07
    客运
    -0.07
    Eat
    -0.07
    owering
    -0.07
    进化
    -0.07
    POSITIVE LOGITS
    (CancellationToken
    0.08
    ($('.
    0.07
    Mu
    0.07
    ument
    0.07
     Lup
    0.07
    黑恶势力
    0.07
    鲳
    0.07
    暮らし
    0.07
     Datensch
    0.07
     thiệt
    0.07
    Act Density 0.003%

    No Known Activations