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

    Neuronpedia

    INDEX
    Explanations

    hit

    np_max-act · gemini-2.0-flash

    The neuron fires on informal, idiomatic gerund-based phrases that describe mental or emotional states (e.g. “having a lot of things figured out,” “getting a dopamine hit,” “doing nothing about it”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    empty
    -0.07
     pairs
    -0.07
    solve
    -0.06
    夫
    -0.06
     pair
    -0.06
    INI
    -0.06
    _temp
    -0.06
     spec
    -0.06
    921
    -0.06
     whose
    -0.06
    POSITIVE LOGITS
     κοι
    0.07
     Б
    0.06
    ')}}"></
    0.06
    อำนวย
    0.06
    ＼＼
    0.06
     نمود
    0.06
     AMC
    0.06
     aktar
    0.06
    ُّ
    0.06
     devuelve
    0.06
    Act Density 0.152%

    No Known Activations