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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یزات
    -0.07
    ifix
    -0.07
     settled
    -0.07
    _Address
    -0.06
     بيت
    -0.06
    022
    -0.06
    ーニ
    -0.06
    rparr
    -0.06
    ,np
    -0.06
     engagement
    -0.06
    POSITIVE LOGITS
    thesis
    0.06
     Mango
    0.06
     Possible
    0.06
    accine
    0.06
     dopo
    0.06
     İz
    0.06
    Rick
    0.06
     ".↵
    0.06
     bans
    0.06
    _EXEC
    0.06
    Act Density 0.005%

    No Known Activations