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

    Neuronpedia

    INDEX
    Explanations

    warnings and advice

    np_max-act · gemini-2.0-flash

    The neuron detects hedging or conditional safety language—phrases that qualify a substance as “safe” only under specified precautions or conditions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     وت
    -0.07
     도시
    -0.06
    igidbody
    -0.06
     multiplier
    -0.06
     теперь
    -0.06
    lap
    -0.06
    بلغ
    -0.06
     تکن
    -0.06
     tag
    -0.06
    .Camera
    -0.06
    POSITIVE LOGITS
    셀
    0.06
    .ex
    0.06
    ?’
    0.06
    orientation
    0.06
     bölg
    0.06
    ?“
    0.06
    VERS
    0.06
    _Enter
    0.06
    >Select
    0.06
    (lower
    0.05
    Act Density 0.044%

    No Known Activations