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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with boundaries and positions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens before whole numbers

    np_acts-logits-general · gemini-2.0-flash

    all messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.71
     ženy
    -0.66
     صوتيه
    -0.64
     kobiety
    -0.62
     perfons
    -0.56
     sebaliknya
    -0.56
     osoby
    -0.56
    arabe
    -0.55
     urządzenia
    -0.54
     Jugendliche
    -0.54
    POSITIVE LOGITS
    InputLabel
    0.54
    tických
    0.53
     den
    0.50
    μένων
    0.50
    uttavia
    0.48
    ментов
    0.48
    ThroughAttribute
    0.48
     Taktlose
    0.47
    ικών
    0.47
    τών
    0.46
    Act Density 0.049%

    No Known Activations