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

    Neuronpedia

    INDEX
    Explanations

    Online communication text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izwa
    -0.08
    ponen
    -0.08
     Abra
    -0.08
     adjustments
    -0.08
    olescent
    -0.08
    ixel
    -0.07
     бақыла
    -0.07
     timely
    -0.07
     münasib
    -0.07
     approval
    -0.07
    POSITIVE LOGITS
     revealing
    0.08
     rendel
    0.07
     geçti
    0.07
     Www
    0.07
     pew
    0.07
    куда
    0.07
     reluctantly
    0.07
    通販
    0.07
     révél
    0.07
    ちゃ
    0.07
    Act Density 0.013%

    No Known Activations