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

    Neuronpedia

    INDEX
    Explanations

    instances of explanation, justification, or causation usually including the word 'so'

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unan
    -0.46
    quels
    -0.44
    ecma
    -0.42
    quelles
    -0.39
     toán
    -0.38
     apparente
    -0.38
     ایر
    -0.37
    !("{}",
    -0.37
    etka
    -0.36
    (@"%@",
    -0.36
    POSITIVE LOGITS
     that
    1.31
     EconPapers
    0.96
    Tikang
    0.94
    GEBURTSDATUM
    0.92
    rungsseite
    0.91
    that
    0.79
    contentLoaded
    0.78
     dass
    0.78
    sizeCache
    0.78
     bahwa
    0.75
    Act Density 0.757%

    No Known Activations