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

    Neuronpedia

    INDEX
    Explanations

    from various sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xhrObj
    0.35
     llegando
    0.31
    in
    0.30
    ۰
    0.29
     omdat
    0.29
     manteniendo
    0.29
    小
    0.29
    cale
    0.28
     изображение
    0.28
     afficher
    0.28
    POSITIVE LOGITS
     whence
    0.54
     thence
    0.46
     the
    0.46
     afar
    0.44
    ม
    0.40
     standpoint
    0.38
    ک
    0.37
     this
    0.37
     that
    0.36
    ъ
    0.34
    Act Density 0.193%

    No Known Activations