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

    Neuronpedia

    INDEX
    Explanations

    the first-person pronoun "I" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     will
    -0.71
    will
    -0.60
     even
    -0.58
     Will
    -0.53
     akan
    -0.49
     when
    -0.49
     zullen
    -0.48
     khi
    -0.46
    Will
    -0.44
     shall
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.91
     المعيارى
    0.89
     saites
    0.86
     OFDb
    0.85
     فريبيس
    0.84
    évaluateur
    0.84
     typelib
    0.84
    Cyfeiriadau
    0.84
     виправивши
    0.83
     surla
    0.82
    Act Density 1.021%

    No Known Activations