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

    Neuronpedia

    INDEX
    Explanations

    code snippets or technical documentation related to loading models, database access, or the Java Native Interface

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rates
    -1.10
     rates
    -1.10
     rate
    -1.09
     RATES
    -1.04
    Rates
    -1.02
     Rate
    -1.02
     RATE
    -0.96
    rates
    -0.91
    Rate
    -0.90
    RATES
    -0.89
    POSITIVE LOGITS
     onCreateView
    0.57
     autorytatywna
    0.57
    asional
    0.50
    νά
    0.50
     الاطلاع
    0.49
     صوتيه
    0.49
    geç
    0.48
    moveToNext
    0.47
     testing
    0.47
    moveToFirst
    0.47
    Act Density 2.302%

    No Known Activations