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

    Neuronpedia

    INDEX
    Explanations

    bool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    daş
    -0.07
     aided
    -0.07
    ži
    -0.07
    تع
    -0.06
    _yaml
    -0.06
     Scouts
    -0.06
    _HI
    -0.06
     grooming
    -0.06
     хотя
    -0.06
    Arrange
    -0.06
    POSITIVE LOGITS
     resetting
    0.07
    normally
    0.06
     normally
    0.06
    Normally
    0.06
    "os
    0.06
     Duffy
    0.06
     elseif
    0.06
     Rab
    0.06
    Left
    0.06
    	elseif
    0.06
    Act Density 0.003%

    No Known Activations