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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     البداية
    -0.09
    sette
    -0.09
    Beginning
    -0.08
    ألة
    -0.08
    اصيل
    -0.08
    Sharp
    -0.08
    ด้าน
    -0.07
    .asp
    -0.07
     รี
    -0.07
    unciation
    -0.07
    POSITIVE LOGITS
     Umständen
    0.11
     હેઠળ
    0.11
     scrutiny
    0.11
     circumstances
    0.11
     umbrella
    0.10
     ausp
    0.10
     pressures
    0.09
     guise
    0.09
     aeg
    0.09
     दब
    0.09
    Act Density 0.079%

    No Known Activations