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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abide
    -0.06
     وح
    -0.06
    (form
    -0.06
     που
    -0.06
    hib
    -0.06
     आज
    -0.06
    stab
    -0.06
    attachments
    -0.06
    tabs
    -0.06
     STAT
    -0.06
    POSITIVE LOGITS
     střední
    0.07
     emit
    0.06
    '-
    0.06
    솔
    0.06
    _Frame
    0.06
    uggle
    0.06
     downside
    0.06
     рыб
    0.06
     wp
    0.06
     optimize
    0.06
    Act Density 0.546%

    No Known Activations