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

    Neuronpedia

    INDEX
    Explanations

    direct

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of creative/media job titles or credited roles (e.g., writer, director, producer, actor, host) in a biography.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     proc
    -0.06
    Hint
    -0.06
    ु�
    -0.06
    _Pro
    -0.06
     Nap
    -0.06
     fertilizer
    -0.06
    _EXTERNAL
    -0.06
     modelos
    -0.06
     अक
    -0.06
    .GetService
    -0.06
    POSITIVE LOGITS
     triumph
    0.07
    lical
    0.07
     complied
    0.07
     lợi
    0.07
     Mutual
    0.06
    컬
    0.06
    střed
    0.06
    lamaz
    0.06
    collect
    0.06
    ंर
    0.06
    Act Density 0.010%

    No Known Activations