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

    Neuronpedia

    INDEX
    Explanations

    computer files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	pos
    -0.07
    羑
    -0.07
    .TextInput
    -0.07
    .'));↵
    -0.07
    _offer
    -0.07
    ANTLR
    -0.07
    不断提升
    -0.06
    (_("
    -0.06
    طيب
    -0.06
    产业扶贫
    -0.06
    POSITIVE LOGITS
     schemas
    0.08
     Hutchinson
    0.08
     etiquette
    0.07
    几乎
    0.07
     histories
    0.07
    halten
    0.07
    fraction
    0.07
     identifiers
    0.07
    0.07
     globally
    0.07
    Act Density 1.105%

    No Known Activations