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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens, particularly floating‐point or decimal number substrings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rotational
    -0.07
     lith
    -0.06
     contests
    -0.06
     birisi
    -0.06
     polic
    -0.06
    樣
    -0.06
    áng
    -0.06
     péče
    -0.06
     Sparse
    -0.06
     pq
    -0.06
    POSITIVE LOGITS
    null
    0.06
     Corpus
    0.06
    ystick
    0.06
    columns
    0.06
     installs
    0.06
     woodworking
    0.06
    .instance
    0.06
     pasta
    0.06
    льт
    0.06
    ::-
    0.06
    Act Density 0.001%

    No Known Activations