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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron detects references to figures (e.g. “FIG.”) and their accompanying figure numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Timeline
    -0.07
    etect
    -0.06
     killings
    -0.06
    -ins
    -0.06
     transmit
    -0.06
    leşik
    -0.06
    -php
    -0.06
    owitz
    -0.06
    _with
    -0.06
    ページ
    -0.06
    POSITIVE LOGITS
    (moment
    0.07
    加工
    0.06
    �
    0.06
    (seq
    0.06
    儿
    0.06
    ου
    0.06
     Elekt
    0.06
     فراو
    0.06
     tuition
    0.06
    .reason
    0.05
    Act Density 0.004%

    No Known Activations