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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on terms that refer to specific timing or scoring events (minutes, halves, goals, scores, trophies, etc.) in sports match recaps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     THIS
    -0.06
     сви
    -0.06
    ै.
    -0.06
     भव
    -0.06
    _po
    -0.06
     λόγ
    -0.06
     mekan
    -0.06
    -quarter
    -0.06
    ै,
    -0.06
     Однак
    -0.06
    POSITIVE LOGITS
    aby
    0.07
     zih
    0.07
    （昭和
    0.07
     土
    0.06
    +"
    0.06
     outra
    0.06
    ind
    0.06
    hack
    0.06
    air
    0.06
     spider
    0.06
    Act Density 0.271%

    No Known Activations