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

    Neuronpedia

    INDEX
    Explanations

    angles

    np_max-act · gemini-2.0-flash

    This neuron activates on references to geometric angles (e.g. the word “angle,” the symbol “θ,” and nearby numeric values specifying the angle).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    мещ
    -0.07
    EMP
    -0.07
    conds
    -0.07
    _pair
    -0.06
     Services
    -0.06
     Million
    -0.06
     deepen
    -0.06
    ?>;↵
    -0.06
    ilia
    -0.06
     ECS
    -0.06
    POSITIVE LOGITS
     polož
    0.07
     nou
    0.06
     마음
    0.06
     أب
    0.06
    Featured
    0.06
     alphabet
    0.06
     rover
    0.06
     compliments
    0.06
    (confirm
    0.06
    ября
    0.06
    Act Density 0.006%

    No Known Activations