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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵
    -0.59
    ↵↵↵
    -0.56
    '
    -0.56
    TagMode
    -0.56
    "
    -0.56
     being
    -0.55
    Str
    -0.55
    withIdentifier
    -0.55
     becoming
    -0.54
    ль
    -0.54
    POSITIVE LOGITS
     Jefus
    1.09
     itſelf
    1.05
     myſelf
    1.04
     Efq
    1.02
     purpoſe
    0.93
     houſe
    0.91
     ſtate
    0.91
     pleaſure
    0.90
     himſelf
    0.89
    ſelves
    0.88
    Act Density 0.035%

    No Known Activations