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

    Neuronpedia

    INDEX
    Explanations

    Torture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    顾虑
    -0.08
    畤
    -0.08
    _SAFE
    -0.07
    🎲
    -0.07
    ぼ
    -0.07
    碧
    -0.07
     חוב
    -0.07
    鹫
    -0.07
     pathetic
    -0.07
    .invalid
    -0.07
    POSITIVE LOGITS
    ROOT
    0.07
    ונו
    0.07
     dynam
    0.07
    /Library
    0.06
     SOCK
    0.06
    Handle
    0.06
     submarines
    0.06
     RuntimeMethod
    0.06
    NL
    0.06
    tableName
    0.06
    Act Density 0.008%

    No Known Activations