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

    Neuronpedia

    INDEX
    Explanations

    str

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    喝
    -0.06
    ustum
    -0.06
    icom
    -0.06
    ố
    -0.06
     Lok
    -0.06
     launcher
    -0.06
    deb
    -0.06
     cable
    -0.06
    (lhs
    -0.06
    _LA
    -0.06
    POSITIVE LOGITS
    سات
    0.06
     NSW
    0.06
     %[
    0.06
    ],[-
    0.06
    боратор
    0.06
    _SYN
    0.06
    ACKET
    0.06
     Αλ
    0.06
    関係
    0.06
    "></
    0.06
    Act Density 0.001%

    No Known Activations