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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires on the “hope that it will be useful” clause (i.e. the word “useful”) in GNU‐style license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    dealloc
    -0.06
     smooth
    -0.06
    erna
    -0.06
    RGBO
    -0.06
     dried
    -0.06
     değişik
    -0.06
     acrylic
    -0.06
    OTH
    -0.06
    istica
    -0.06
    芬
    -0.06
    POSITIVE LOGITS
     раствор
    0.07
    agedList
    0.07
    /GL
    0.07
     Gender
    0.06
     inserting
    0.06
     toplantı
    0.06
    _Tree
    0.06
    اك
    0.06
    .Persistent
    0.06
    埋
    0.06
    Act Density 0.001%

    No Known Activations