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

    Neuronpedia

    INDEX
    Explanations

    cruel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haber
    -0.07
    ζί
    -0.07
     sotto
    -0.06
    atherine
    -0.06
     عب
    -0.06
     shiny
    -0.06
     APP
    -0.06
    	git
    -0.06
     gigantic
    -0.06
     başladı
    -0.06
    POSITIVE LOGITS
     cruel
    0.11
    Е
    0.07
    ERY
    0.07
     jointly
    0.07
     Memorial
    0.06
    _STOP
    0.06
    рой
    0.06
     clamp
    0.06
    plier
    0.06
    EL
    0.06
    Act Density 0.002%

    No Known Activations