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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lst
    -0.07
     هناك
    -0.06
     têm
    -0.06
    btn
    -0.06
    _below
    -0.06
     올라
    -0.06
    aktion
    -0.06
    zb
    -0.06
     unmarried
    -0.06
    Exit
    -0.06
    POSITIVE LOGITS
    .pag
    0.07
    ickém
    0.07
    ační
    0.07
     district
    0.07
    zens
    0.07
    uating
    0.07
    명
    0.06
    ội
    0.06
     DAM
    0.06
    PLY
    0.06
    Act Density 0.028%

    No Known Activations