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

    Neuronpedia

    INDEX
    Explanations

    POST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    усти
    -0.08
    .dead
    -0.07
    phone
    -0.06
     Alic
    -0.06
     seh
    -0.06
     Sv
    -0.06
    .lookup
    -0.06
    aviolet
    -0.06
     isl
    -0.06
     theolog
    -0.06
    POSITIVE LOGITS
     aime
    0.07
     ایست
    0.07
     tossing
    0.06
    CardContent
    0.06
    .setTitle
    0.06
    iag
    0.06
    \Auth
    0.06
    HorizontalAlignment
    0.06
    αρίου
    0.06
    编辑
    0.06
    Act Density 0.006%

    No Known Activations