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

    Neuronpedia

    INDEX
    Explanations

    fiction

    np_max-act · gemini-2.0-flash

    The neuron responds to feminine third-person references (e.g. “she,” “her,” “girl”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Independent
    -0.07
    aga
    -0.07
    _Window
    -0.07
    肃
    -0.07
    -0.07
     울
    -0.06
    áp
    -0.06
    Income
    -0.06
    BASH
    -0.06
    rio
    -0.06
    POSITIVE LOGITS
     Lieutenant
    0.06
     peril
    0.06
     Mein
    0.06
    ีผ
    0.06
     Sergeant
    0.06
     nướng
    0.06
    EntryPoint
    0.06
     خوب
    0.06
     ofrec
    0.06
     plaintiffs
    0.06
    Act Density 0.120%

    No Known Activations