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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron responds to short all-uppercase letter sequences (acronyms or initialisms) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .notification
    -0.06
    Difficulty
    -0.06
    _jobs
    -0.06
     aggregate
    -0.06
    Population
    -0.06
     domácí
    -0.06
     Absolutely
    -0.06
     actividad
    -0.06
    ",&
    -0.06
     spoof
    -0.06
    POSITIVE LOGITS
    ($__
    0.08
    한
    0.07
    df
    0.06
    -android
    0.06
    장은
    0.06
    utr
    0.06
     lien
    0.06
    dfa
    0.06
     hObject
    0.06
    لیسی
    0.06
    Act Density 1.285%

    No Known Activations