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

    Neuronpedia

    INDEX
    Explanations

    -s

    np_max-act · gemini-2.0-flash

    This neuron detects phrasing that introduces examples or lists (e.g. “such as,” “a … array of”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    (Player
    -0.06
     Mutation
    -0.06
    -fi
    -0.06
     ΑΓ
    -0.06
    クロ
    -0.06
    (ad
    -0.06
    hibition
    -0.06
     نخ
    -0.06
     Evaluation
    -0.05
    POSITIVE LOGITS
    .findAll
    0.07
    basic
    0.07
     Tomáš
    0.07
    就会
    0.07
     आपक
    0.07
     refund
    0.06
     교육
    0.06
    zu
    0.06
     tyto
    0.06
     наш
    0.06
    Act Density 0.289%

    No Known Activations