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

    Neuronpedia

    INDEX
    Explanations

    divided

    np_max-act · gemini-2.0-flash

    The neuron is keyed to spotting floating‐point numeric literals (decimal fractions) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crews
    -0.07
     WAN
    -0.07
    ONEY
    -0.06
     některých
    -0.06
     nim
    -0.06
    Particle
    -0.06
    rett
    -0.06
    Recorder
    -0.06
     Small
    -0.06
    _penalty
    -0.06
    POSITIVE LOGITS
     thoughtful
    0.07
    .read
    0.07
    ισμός
    0.07
     Ultra
    0.06
    /div
    0.06
     údajů
    0.06
     Bloody
    0.06
    .localizedDescription
    0.06
     Completely
    0.06
     UIStoryboard
    0.06
    Act Density 0.006%

    No Known Activations