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

    Neuronpedia

    INDEX
    Explanations

    where most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jeweils
    0.40
    ਿਤ
    0.37
    रावर
    0.36
    ridor
    0.36
     obviously
    0.36
     stets
    0.36
    olyte
    0.35
    evsky
    0.35
     ganger
    0.34
     alles
    0.34
    POSITIVE LOGITS
     большинства
    2.41
     большинство
    2.36
     большин
    2.31
    大多数
    2.31
     большинстве
    2.28
     अधिकांश
    2.23
     대부분
    2.14
    大多數
    2.14
     many
    2.02
     பெரும்பாலான
    1.99
    Act Density 0.098%

    No Known Activations