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

    Neuronpedia

    INDEX
    Explanations

    legal agreement terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    逺
    0.36
     blobs
    0.34
     padassa
    0.34
     输出
    0.33
     calorías
    0.33
     nascost
    0.33
    alámb
    0.32
     vùng
    0.32
     دارید
    0.32
     spermato
    0.32
    POSITIVE LOGITS
     shall
    0.42
     hereunder
    0.39
    each
    0.38
    hereinafter
    0.36
    such
    0.35
     lender
    0.35
    business
    0.35
    employees
    0.34
    email
    0.33
     each
    0.33
    Act Density 0.070%

    No Known Activations