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

    Neuronpedia

    INDEX
    Explanations

    ++

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     querying
    -0.07
    گو
    -0.07
    �
    -0.06
    zf
    -0.06
    et
    -0.06
    dr
    -0.06
    ContentPane
    -0.06
    Gu
    -0.06
    LV
    -0.06
    surface
    -0.06
    POSITIVE LOGITS
    Wake
    0.07
     끝
    0.07
     сост
    0.06
     finanční
    0.06
    ICK
    0.06
     karşı
    0.06
     глу
    0.06
     vs
    0.06
     %@",
    0.06
     हट
    0.06
    Act Density 0.002%

    No Known Activations