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

    Neuronpedia

    INDEX
    Explanations

    terms related to systemic failure or issues

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

    system failures and corruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.61
    ьаж
    -0.60
    :✨
    -0.54
    Gambas
    -0.54
    AutoScaleMode
    -0.53
     ब्रेकडाउन
    -0.52
    Tikang
    -0.52
    MENAFN
    -0.52
     désactiv
    -0.52
    Personensuche
    -0.50
    POSITIVE LOGITS
    massen
    0.36
     bambú
    0.34
     yol
    0.33
     abuse
    0.32
    յ
    0.32
     missione
    0.31
    frem
    0.31
     transparencia
    0.31
     abuses
    0.30
    gew
    0.30
    Act Density 0.263%

    No Known Activations