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

    Neuronpedia

    INDEX
    Explanations

    chickens

    np_max-act · gemini-2.0-flash

    the neuron detects short cause-and-solution statement pairs phrased like "X is due to Y. The solution is to Z."

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     openFileDialog
    -0.07
    ulur
    -0.07
    виж
    -0.06
    umlah
    -0.06
    328
    -0.06
    _placement
    -0.06
    hay
    -0.06
    markets
    -0.06
    enské
    -0.06
     석
    -0.06
    POSITIVE LOGITS
    欧
    0.07
    _BB
    0.07
    есто
    0.06
     listop
    0.06
    登録
    0.06
     Uses
    0.06
     Retro
    0.06
    طفال
    0.06
     Liter
    0.06
    action
    0.06
    Act Density 0.715%

    No Known Activations