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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens representing decimal or fractional values (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -ext
    -0.07
     seeking
    -0.07
    corner
    -0.07
     //////
    -0.07
    //*
    -0.07
     seekers
    -0.07
     dk
    -0.07
    %%%%
    -0.06
    OLVE
    -0.06
     kidnapping
    -0.06
    POSITIVE LOGITS
    BD
    0.07
    Us
    0.06
     Ball
    0.06
     благодаря
    0.06
     Все
    0.06
    niční
    0.06
    Bs
    0.06
     زمینه
    0.06
     Modules
    0.06
    正式
    0.05
    Act Density 0.090%

    No Known Activations