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

    Neuronpedia

    INDEX
    Explanations

    fs

    np_max-act · gemini-2.0-flash

    The neuron fires on floating-point numeric literals (numbers containing a decimal point, including negatives).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "What
    -0.07
    一页
    -0.07
    acion
    -0.06
    Room
    -0.06
     يت
    -0.06
    áci
    -0.06
    _VERTICAL
    -0.06
    神
    -0.06
     špat
    -0.06
     Span
    -0.06
    POSITIVE LOGITS
    ่วย
    0.07
    _fk
    0.06
    _DEC
    0.06
     heals
    0.06
    ัดการ
    0.06
    _decl
    0.06
    交通
    0.06
     首
    0.06
    TRUE
    0.06
     recipro
    0.06
    Act Density 0.000%

    No Known Activations