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

    Neuronpedia

    INDEX
    Explanations

    PWM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    between
    -0.07
     fluffy
    -0.07
     �
    -0.06
    Editing
    -0.06
     credibility
    -0.06
     Praha
    -0.06
     ramen
    -0.06
     Publisher
    -0.06
    _ball
    -0.06
     noted
    -0.06
    POSITIVE LOGITS
    _cleanup
    0.07
    leşik
    0.06
    lomou
    0.06
    	Simple
    0.06
     جشن
    0.06
    acios
    0.06
    ằm
    0.06
    τικών
    0.06
     Slip
    0.06
    256
    0.06
    Act Density 0.014%

    No Known Activations