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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indic
    -0.07
    warning
    -0.06
    ekim
    -0.06
    Deg
    -0.06
     recording
    -0.06
     역사
    -0.06
     shadows
    -0.06
     vic
    -0.06
     gaze
    -0.06
     Rising
    -0.06
    POSITIVE LOGITS
     controlling
    0.07
    neh
    0.06
    рег
    0.06
    bones
    0.06
    ,↵↵
    0.06
     swings
    0.06
     Pav
    0.06
     قالب
    0.06
    otts
    0.06
    Complete
    0.06
    Act Density 0.030%

    No Known Activations