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

    Neuronpedia

    INDEX
    Explanations

    legal complaints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ソン
    -0.08
     chú
    -0.07
    iosis
    -0.07
     day
    -0.07
     mar
    -0.07
    系統
    -0.07
     days
    -0.07
    aded
    -0.06
     bmi
    -0.06
    %p
    -0.06
    POSITIVE LOGITS
    :H
    0.07
    rrha
    0.07
    İŞ
    0.07
    Aggregate
    0.06
     Wrestle
    0.06
    อบ
    0.06
    Alter
    0.06
    \Command
    0.06
    吸
    0.06
    getX
    0.06
    Act Density 0.004%

    No Known Activations