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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals containing decimal points (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     enriched
    -0.07
    Industry
    -0.07
    Rect
    -0.06
     >>
    -0.06
     mirror
    -0.06
    FINITY
    -0.06
     cinema
    -0.06
     ruined
    -0.06
     centre
    -0.06
     service
    -0.06
    POSITIVE LOGITS
    ูด
    0.08
     rõ
    0.07
    Take
    0.06
     TAKE
    0.06
    :".
    0.06
    .land
    0.06
     pravidel
    0.06
    rač
    0.06
     Prostitutas
    0.06
    /local
    0.06
    Act Density 0.012%

    No Known Activations