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

    Neuronpedia

    INDEX
    Explanations

    contents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الأ
    -0.08
    뇰
    -0.08
     turning
    -0.07
    rebbe
    -0.07
    当然
    -0.07
    منح
    -0.06
     translate
    -0.06
    𝙤
    -0.06
    cura
    -0.06
    於
    -0.06
    POSITIVE LOGITS
     livestock
    0.07
     Neck
    0.07
     solo
    0.07
     Equals
    0.07
    ({...
    0.07
    დ
    0.07
     Knot
    0.07
     запис
    0.07
    Swipe
    0.07
    咥
    0.07
    Act Density 0.071%

    No Known Activations