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

    Neuronpedia

    INDEX
    Explanations

    categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TU
    -0.07
    ۱۲
    -0.07
     RECORD
    -0.06
     счита
    -0.06
    (face
    -0.06
     isize
    -0.06
     ADM
    -0.06
     pł
    -0.06
     få
    -0.06
     relinqu
    -0.06
    POSITIVE LOGITS
    screen
    0.06
    /><
    0.06
    ")));↵
    0.06
    edith
    0.06
     Ž
    0.06
    hya
    0.06
    segments
    0.06
     양
    0.06
    ounds
    0.06
    MEDIA
    0.06
    Act Density 0.022%

    No Known Activations