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

    Neuronpedia

    INDEX
    Explanations

    Numbers ending in 000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	control
    -0.08
    estion
    -0.08
    азақстан
    -0.08
    ిశ
    -0.08
     parlement
    -0.08
     বলা
    -0.08
     Parlamento
    -0.08
    ikino
    -0.08
     считается
    -0.08
     Contrary
    -0.08
    POSITIVE LOGITS
    พื้น
    0.08
     removable
    0.08
    0.08
     раз
    0.07
    สะ
    0.07
     plugged
    0.07
    ragen
    0.07
     hue
    0.07
     spaced
    0.07
     Sw
    0.07
    Act Density 0.042%
    No Known Activations