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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     justification
    -0.08
     सच
    -0.08
    မြ
    -0.07
    気
    -0.07
     upbringing
    -0.07
     Adolesc
    -0.07
    Tabbed
    -0.07
    volt
    -0.07
    -0.07
    percent
    -0.07
    POSITIVE LOGITS
     крыш
    0.08
    Planes
    0.08
     بين
    0.08
     SES
    0.08
    _plane
    0.08
     лини
    0.08
     comuni
    0.08
     überhaupt
    0.08
     iki
    0.07
    線
    0.07
    Act Density 0.014%
    No Known Activations