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

    Neuronpedia

    INDEX
    Explanations

    Fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [max
    -0.07
     Transformers
    -0.06
    　
    -0.06
     Haram
    -0.06
    温
    -0.06
    RuleContext
    -0.06
     Properties
    -0.06
     OLED
    -0.06
    	ff
    -0.06
    _Widget
    -0.06
    POSITIVE LOGITS
     nút
    0.07
     stren
    0.07
     preventing
    0.07
     gusto
    0.07
     awarded
    0.06
    最近
    0.06
     darken
    0.06
     slashes
    0.06
    /Instruction
    0.06
    (userInfo
    0.06
    Act Density 0.022%

    No Known Activations