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

    Neuronpedia

    INDEX
    Explanations

    extends beyond

    np_max-act · gemini-2.0-flash

    This neuron detects highly precise numeric tokens, especially floating‐point/decimal values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ATEGY
    -0.07
    VERY
    -0.07
    BM
    -0.07
     Lage
    -0.07
    ısıyla
    -0.07
    elier
    -0.07
    velte
    -0.07
    (colors
    -0.07
    (where
    -0.06
     метал
    -0.06
    POSITIVE LOGITS
     sides
    0.06
    _event
    0.06
     eyed
    0.06
    _theme
    0.06
    _px
    0.06
    _tooltip
    0.06
     Sep
    0.06
     �
    0.06
     св
    0.05
    -conf
    0.05
    Act Density 0.028%

    No Known Activations