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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron is keyed to recognize Objective-C API type names (e.g. Cocoa/Foundation class identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    masters
    -0.07
    >Returns
    -0.06
    桂
    -0.06
     Elig
    -0.06
     archives
    -0.06
     ');↵↵
    -0.06
     học
    -0.06
    _ap
    -0.06
    vekili
    -0.05
    .Scale
    -0.05
    POSITIVE LOGITS
     mosaic
    0.07
     murderous
    0.07
     och
    0.06
    guarded
    0.06
    처
    0.06
    size
    0.06
     chiếc
    0.06
    тер
    0.06
     smě
    0.06
     başk
    0.06
    Act Density 0.001%

    No Known Activations