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

    Neuronpedia

    INDEX
    Explanations

    in at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expressions
    -0.08
     કામગીરી
    -0.07
     practice
    -0.07
    લ
    -0.07
    elh
    -0.07
     abr
    -0.07
    เพิ่มเติม
    -0.07
     trivial
    -0.07
     requirement
    -0.07
     casamento
    -0.07
    POSITIVE LOGITS
     surrounded
    0.11
     фоне
    0.09
     shaded
    0.09
     majest
    0.09
    突出
    0.09
     amidst
    0.09
     positioned
    0.09
     centerpiece
    0.09
     Szene
    0.09
     солне
    0.09
    Act Density 0.012%

    No Known Activations