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

    Neuronpedia

    INDEX
    Explanations

    cool colors, light, or textures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ться
    1.23
    də
    1.07
    patial
    1.00
    dichlor
    0.94
     were
    0.92
     can
    0.92
    া
    0.92
    s
    0.91
    to
    0.91
     be
    0.89
    POSITIVE LOGITS
    에요
    1.01
    ate
    0.95
    ul
    0.90
    eli
    0.84
    나
    0.80
    awan
    0.80
    owo
    0.79
    지만
    0.77
    .
    0.77
    ola
    0.77
    Act Density 0.003%

    No Known Activations