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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron spots mentions of experimental treatments or administrations (e.g. “treatment,” “treated,” “administration,” “pre-treatment”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    erk
    -0.07
    _track
    -0.06
    xBD
    -0.06
    çesi
    -0.06
     Blocking
    -0.06
     batt
    -0.06
     indicated
    -0.06
    .toFixed
    -0.06
    _OscInitStruct
    -0.06
     bunk
    -0.06
    POSITIVE LOGITS
     exquisite
    0.06
     amd
    0.06
    VAL
    0.06
     spacecraft
    0.06
     conventions
    0.06
     Law
    0.06
     law
    0.06
    MainThread
    0.06
    Char
    0.06
     Ago
    0.06
    Act Density 0.029%

    No Known Activations