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

    Neuronpedia

    INDEX
    Explanations

    Catholic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	self
    -0.08
     self
    -0.08
     resign
    -0.07
    (Pro
    -0.07
    _↵
    -0.07
     areia
    -0.07
    ahah
    -0.07
     attend
    -0.07
     Self
    -0.07
     pessoas
    -0.07
    POSITIVE LOGITS
     overlays
    0.09
    转换
    0.09
     convertible
    0.09
     չ
    0.08
    昌县
    0.08
    Converted
    0.08
    converted
    0.08
    .synthetic
    0.08
     adaptación
    0.08
    SAFE
    0.08
    Act Density 0.011%

    No Known Activations