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

    Neuronpedia

    INDEX
    Explanations

    Russian/Greek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     colors
    -0.08
     Mes
    -0.08
     Jen
    -0.08
     plen
    -0.08
    touch
    -0.08
    xd
    -0.08
     Farben
    -0.08
    ubin
    -0.08
     touch
    -0.07
     लै
    -0.07
    POSITIVE LOGITS
    築
    0.13
     구축
    0.13
     aufgebaut
    0.12
    building
    0.12
     construcción
    0.12
    -building
    0.12
    .build
    0.12
     rebuilding
    0.12
    构
    0.12
     ನಿರ್ಮ
    0.12
    Act Density 0.051%

    No Known Activations