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

    Neuronpedia

    INDEX
    Explanations

    terms associated with accounts and registration processes

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

    Non-English words and punctuation

    np_acts-logits-general · gemini-2.0-flash

    citations, multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intention
    -0.51
     CAB
    -0.42
    ged
    -0.41
    ajas
    -0.41
    سلام
    -0.40
     ged
    -0.40
    ija
    -0.39
    ijo
    -0.38
    oi
    -0.38
    appro
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    0.97
     autorytatywna
    0.96
    Personensuche
    0.96
     utafitiHapana
    0.91
     المعيارى
    0.89
    principalColumn
    0.87
     незавершена
    0.86
     للمعارف
    0.85
    الإنجليزية
    0.82
    +#+#
    0.81
    Act Density 0.077%

    No Known Activations