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

    Neuronpedia

    INDEX
    Explanations

    image credits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etus
    -0.07
    ifikasi
    -0.07
    (Item
    -0.07
    legg
    -0.07
    forcement
    -0.07
     טיפול
    -0.07
     Victims
    -0.07
    ủ
    -0.07
    רון
    -0.06
    ollectors
    -0.06
    POSITIVE LOGITS
     Sure
    0.07
     Base
    0.07
     seeing
    0.07
     portraying
    0.07
     earning
    0.06
     Nah
    0.06
     superb
    0.06
    樟
    0.06
     mathematical
    0.06
    CE
    0.06
    Act Density 0.007%

    No Known Activations