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

    Neuronpedia

    INDEX
    Explanations

    positive reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	col
    -0.06
    jej
    -0.06
    LastName
    -0.06
    paRepository
    -0.06
    ーレ
    -0.06
     frustrating
    -0.06
     Chow
    -0.06
    centroid
    -0.06
     عملکرد
    -0.06
    Ik
    -0.06
    POSITIVE LOGITS
     nitel
    0.08
    ERM
    0.08
    tree
    0.07
     empathy
    0.07
     inconsistent
    0.07
     ।↵↵
    0.07
     Mining
    0.07
    ')]↵
    0.07
     carte
    0.07
    赞
    0.07
    Act Density 0.014%

    No Known Activations