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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron detects words that signal positive change, improvement, or encouragement (e.g., make, give, transform, boost, keep).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    FUL
    -0.07
    X
    -0.06
    署
    -0.06
     Mikhail
    -0.06
    ']),↵
    -0.06
    _AVAILABLE
    -0.06
    ningen
    -0.06
    .StretchImage
    -0.06
     сто
    -0.06
    bakan
    -0.06
    POSITIVE LOGITS
     onChangeText
    0.07
    těz
    0.06
    ayo
    0.06
     شود
    0.06
    Stage
    0.06
    อย
    0.06
    female
    0.06
    __)↵
    0.06
     इत
    0.06
    izzle
    0.06
    Act Density 0.136%

    No Known Activations