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

    Neuronpedia

    INDEX
    Explanations

    sys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Washer
    -0.07
     Üye
    -0.07
    .HtmlControls
    -0.07
    .Are
    -0.07
    远程
    -0.07
     journée
    -0.07
    ставил
    -0.06
    .”↵
    -0.06
    ließ
    -0.06
    记忆力
    -0.06
    POSITIVE LOGITS
    inform
    0.07
    停滞
    0.06
     shuffle
    0.06
    优惠
    0.06
    PRINT
    0.06
    getY
    0.06
    깉
    0.06
    .names
    0.06
    LOOP
    0.06
    береж
    0.06
    Act Density 0.001%

    No Known Activations