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

    Neuronpedia

    INDEX
    Explanations

    不能

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kring
    -0.10
    	auto
    -0.08
     measurement
    -0.08
     batter
    -0.08
     qor
    -0.08
     paus
    -0.08
    ത്തിന്റെ
    -0.08
    (auto
    -0.07
     transition
    -0.07
    Measurement
    -0.07
    POSITIVE LOGITS
     heroin
    0.09
     combustible
    0.07
    Rules
    0.07
     Restrictions
    0.07
     offenders
    0.07
    违反
    0.07
    ?!↵
    0.07
    _rules
    0.07
     restricciones
    0.07
     MULT
    0.07
    Act Density 0.001%

    No Known Activations