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

    Neuronpedia

    INDEX
    Explanations

    references to safety or secure practices

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

    "safe" or "safety"

    np_acts-logits-general · gemini-2.0-flash

    safe and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    retudo
    -0.46
    sequelize
    -0.39
    ASTNode
    -0.38
    ellate
    -0.38
     penas
    -0.35
    󠁢
    -0.35
     thẳng
    -0.35
    レーション
    -0.35
    writerow
    -0.34
    MemoryStream
    -0.34
    POSITIVE LOGITS
     Safe
    0.93
    Safe
    0.92
     SAFE
    0.89
    Safety
    0.86
    saf
    0.86
    SAFE
    0.85
    safe
    0.84
    Saf
    0.84
     safe
    0.82
     Unsafe
    0.82
    Act Density 0.062%

    No Known Activations