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

    Neuronpedia

    INDEX
    Explanations

    Acids

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific chemical acid names (i.e. words ending in “-ic acid”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     WL
    -0.07
     massaggi
    -0.07
    ップ
    -0.06
     iterators
    -0.06
     Ston
    -0.06
     outdated
    -0.06
     gerekmektedir
    -0.06
    _slope
    -0.06
     ملی
    -0.06
     Vill
    -0.05
    POSITIVE LOGITS
    ric
    0.08
    ic
    0.08
    hip
    0.07
    if
    0.07
    Auto
    0.07
     autom
    0.07
     produced
    0.07
    Hip
    0.07
    ových
    0.07
     Essay
    0.06
    Act Density 0.008%

    No Known Activations