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

    Neuronpedia

    INDEX
    Explanations

    Incorrectness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STATIC
    -0.08
    -worker
    -0.07
     graf
    -0.07
     Mis
    -0.07
     Bris
    -0.07
    .pause
    -0.07
    akes
    -0.06
    ftime
    -0.06
    _Free
    -0.06
     Warwick
    -0.06
    POSITIVE LOGITS
    іли
    0.06
    Công
    0.06
     vé
    0.06
    える
    0.06
     parcels
    0.06
    0.06
     τρο
    0.06
    .readString
    0.06
     �
    0.06
    !»
    0.05
    Act Density 0.087%

    No Known Activations