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

    Neuronpedia

    INDEX
    Explanations

    firewalls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aja
    -0.07
    опис
    -0.06
     земля
    -0.06
     ko
    -0.06
     [];↵↵
    -0.06
     元
    -0.06
    278
    -0.06
    んでいる
    -0.06
    بوب
    -0.06
     대학
    -0.06
    POSITIVE LOGITS
     firewall
    0.10
     fieldValue
    0.08
    fresh
    0.07
     Firewall
    0.07
    foreach
    0.07
     thaw
    0.07
    utex
    0.07
    灣
    0.07
    wall
    0.07
    mín
    0.06
    Act Density 0.003%

    No Known Activations