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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Джон
    -0.07
     Clintons
    -0.07
    安排
    -0.06
    .keywords
    -0.06
     ağır
    -0.06
     놀
    -0.06
     lightly
    -0.06
     Majesty
    -0.06
    ovit
    -0.06
    _ORIENTATION
    -0.06
    POSITIVE LOGITS
    _E
    0.07
    <Type
    0.07
    fuse
    0.07
     HC
    0.06
    _Process
    0.06
     Dat
    0.06
    rew
    0.06
    لو
    0.06
    /E
    0.06
    ruc
    0.06
    Act Density 0.449%

    No Known Activations