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

    Neuronpedia

    INDEX
    Explanations

    bracketed citation markers within scientific papers

    oai_token-act-pair · gemini-2.0-flash

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ‘
    -0.73
     '
    -0.72
    écution
    -0.56
     "
    -0.56
    KommentareTeilen
    -0.53
    ↵
    -0.52
     GetEnumerator
    -0.52
     “
    -0.51
     the
    -0.49
    SuccessListener
    -0.49
    POSITIVE LOGITS
     Efq
    0.84
     Shakspeare
    0.80
     Majefty
    0.80
     GIPHY
    0.77
     Monfieur
    0.76
     Jefus
    0.75
     Cæsar
    0.72
     iveco
    0.69
     Pronto
    0.68
     megane
    0.68
    Act Density 0.627%

    No Known Activations