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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on evaluative, opinionated adjectives and descriptors (e.g. flattering, perfect, misleading) that convey subjective judgments about appearance or fit.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     subsidiary
    -0.07
    acerb
    -0.07
     Saunders
    -0.06
     diligent
    -0.06
     Nero
    -0.06
    ric
    -0.06
    .output
    -0.06
     रहत
    -0.06
     milan
    -0.06
     kB
    -0.06
    POSITIVE LOGITS
     tkinter
    0.07
    _INTEGER
    0.06
     ακό
    0.06
     thậm
    0.06
     ситуа
    0.06
    apons
    0.06
    _REPLY
    0.06
    patient
    0.05
    uxe
    0.05
    يلة
    0.05
    Act Density 0.125%

    No Known Activations