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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron is looking for numeric literals in code, especially floating‐point constants.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    467
    -0.07
    alties
    -0.07
    either
    -0.06
    аний
    -0.06
    phony
    -0.06
    meye
    -0.06
    ない
    -0.06
     znal
    -0.06
    457
    -0.06
     accesses
    -0.06
    POSITIVE LOGITS
    摆
    0.07
     tent
    0.07
    .da
    0.06
    _clear
    0.06
    _undo
    0.06
     ideology
    0.06
    Prov
    0.06
    .consume
    0.06
    (host
    0.06
    CLUD
    0.06
    Act Density 0.021%

    No Known Activations