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

    Neuronpedia

    INDEX
    Explanations

    grade

    np_max-act · gemini-2.0-flash

    The neuron primarily detects floating‐point numerical tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _unused
    -0.06
    irms
    -0.06
     mp
    -0.06
     slew
    -0.06
    using
    -0.06
     sizes
    -0.06
    _wp
    -0.06
     lover
    -0.06
    wd
    -0.06
     sın
    -0.06
    POSITIVE LOGITS
     cultured
    0.07
    NullPointerException
    0.06
    (Graphics
    0.06
     depois
    0.06
     assertNull
    0.06
     وذلك
    0.06
    政治
    0.06
    ��
    0.06
    دری
    0.06
    _VOLUME
    0.06
    Act Density 0.008%

    No Known Activations