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

    Neuronpedia

    INDEX
    Explanations

    insect descriptions

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive adjectives—especially color and pattern terms often ending in “-ous”—used in morphological descriptions (e.g. ochreous, fuscous, suffused).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     '%
    -0.07
     Majesty
    -0.07
    体系
    -0.07
     başvur
    -0.07
    prar
    -0.07
     Wir
    -0.07
     кла
    -0.06
    獲得
    -0.06
     promotes
    -0.06
     Ventura
    -0.06
    POSITIVE LOGITS
     süt
    0.06
     лечения
    0.06
    ği
    0.06
    ्शन
    0.06
    .pass
    0.06
    	lib
    0.06
    getToken
    0.06
     WithEvents
    0.06
    賀
    0.06
    ylan
    0.06
    Act Density 0.008%

    No Known Activations