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

    Neuronpedia

    INDEX
    Explanations

    ase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UCCESS
    -0.07
    .fetchall
    -0.07
    County
    -0.07
    -solving
    -0.07
     brave
    -0.07
     blankets
    -0.07
    gateway
    -0.07
    _FLUSH
    -0.07
    iry
    -0.07
    (BuildContext
    -0.07
    POSITIVE LOGITS
     Hover
    0.07
     mou
    0.07
    效应
    0.07
    リンク
    0.07
     traps
    0.07
    適用
    0.06
     axis
    0.06
     тест
    0.06
    ilt
    0.06
    渎
    0.06
    Act Density 0.003%

    No Known Activations