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

    Neuronpedia

    INDEX
    Explanations

    music and creative works

    np_max-act · gemini-2.0-flash

    This neuron responds to numerical tokens formatted as decimal numbers (floats).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    DidChange
    -0.07
    /***
    -0.06
    .Monad
    -0.06
     딸
    -0.06
    vt
    -0.06
    “If
    -0.06
    embrance
    -0.06
     yytype
    -0.06
    명
    -0.06
     tik
    -0.05
    POSITIVE LOGITS
    sou
    0.07
    爾
    0.07
     Hunger
    0.06
     disguise
    0.06
    .partner
    0.06
     แล
    0.06
    /load
    0.06
     SqlParameter
    0.06
    _numer
    0.06
    警
    0.06
    Act Density 0.252%

    No Known Activations