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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    The neuron detects capitalized name tokens (i.e. fragments of proper names) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    찌
    -0.07
    闭
    -0.06
    cx
    -0.06
    bob
    -0.06
    _SERVICE
    -0.06
    filePath
    -0.06
     Tactics
    -0.06
    erdings
    -0.06
    TexParameteri
    -0.06
     않았다
    -0.06
    POSITIVE LOGITS
    ρο
    0.07
    clado
    0.06
    ッグ
    0.06
     thank
    0.06
     seleccion
    0.06
    =".$
    0.06
    urent
    0.06
     форм
    0.06
     halluc
    0.06
    Prom
    0.06
    Act Density 0.025%

    No Known Activations