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

    Neuronpedia

    INDEX
    Explanations

    Text describing various topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     باش
    -0.07
    Positive
    -0.07
     극
    -0.07
     eros
    -0.07
    )}>
    -0.06
     Positive
    -0.06
    态
    -0.06
     Sad
    -0.06
    (className
    -0.06
    .service
    -0.06
    POSITIVE LOGITS
     Conditions
    0.07
    imon
    0.07
    σμο
    0.07
    leveland
    0.06
    unks
    0.06
    енд
    0.06
     bảng
    0.06
    alker
    0.06
    """↵↵
    0.06
    ians
    0.06
    Act Density 0.000%

    No Known Activations