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

    Neuronpedia

    INDEX
    Explanations

    refusal of harmful requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     »
    0.74
     وتن
    0.67
    evole
    0.66
    WEEN
    0.66
    iciona
    0.65
     Cus
    0.65
     requires
    0.65
    주는
    0.64
     uten
    0.64
    CNS
    0.64
    POSITIVE LOGITS
    总结
    0.61
     постара
    0.60
     Richard
    0.59
    Defendant
    0.59
     Decisions
    0.59
     полную
    0.58
     die
    0.58
    einander
    0.56
    die
    0.55
    Changes
    0.54
    Act Density 0.081%

    No Known Activations