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

    Neuronpedia

    INDEX
    Explanations

    command option flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arden
    0.40
     прибыли
    0.40
    oston
    0.39
    ibre
    0.39
    atherine
    0.39
     dhammo
    0.39
     SE
    0.38
    ere
    0.38
     Defin
    0.37
    definite
    0.37
    POSITIVE LOGITS
     আশায়
    0.40
    гӀ
    0.38
    ებულია
    0.37
    :]:
    0.36
    通
    0.36
    自殺
    0.35
    खोरी
    0.35
    瓒
    0.35
     домаћинства
    0.34
    思路
    0.34
    Act Density 0.016%

    No Known Activations