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
     Nimbus
    -0.07
     Wash
    -0.07
     Flip
    -0.07
    white
    -0.06
    MatrixMode
    -0.06
    董事
    -0.06
     labore
    -0.06
     Improved
    -0.06
    inidad
    -0.06
    筇
    -0.06
    POSITIVE LOGITS
    ięć
    0.08
     (_,
    0.07
    方言
    0.07
     אר
    0.07
    .ph
    0.07
    _Ph
    0.07
    确切
    0.07
     dangers
    0.07
     threats
    0.07
     predis
    0.07
    Act Density 0.003%

    No Known Activations