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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act-logits · gemini-2.0-flash

    phrases where the speaker self-identifies as an AI (assistant saying it is an AI).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     mixture
    -0.07
     jeho
    -0.06
     Hot
    -0.06
     Marshall
    -0.06
     TAX
    -0.06
     cabbage
    -0.06
    анные
    -0.06
     μέχρι
    -0.06
    .getSelectedItem
    -0.06
    никами
    -0.06
    POSITIVE LOGITS
    990
    0.07
    plode
    0.07
     Ні
    0.07
    \Active
    0.06
    _OPT
    0.06
    expression
    0.06
    ेण
    0.06
    lookup
    0.06
    'aff
    0.06
    =explode
    0.06
    Act Density 0.021%

    No Known Activations