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

    Neuronpedia

    INDEX
    Explanations

    discord, slack, chat bots, frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onomous
    0.42
    pbx
    0.41
     raid
    0.41
    ServiceName
    0.40
    atoon
    0.40
     Hue
    0.39
    拓展
    0.39
     служ
    0.38
     verlassen
    0.38
     മറ
    0.38
    POSITIVE LOGITS
     botas
    0.43
    盧
    0.41
     საშუალ
    0.40
    吳
    0.40
    ızı
    0.39
     दिल्‍ली
    0.38
     ales
    0.38
    ക്കള്‍
    0.38
    ubin
    0.38
    stum
    0.38
    Act Density 0.010%

    No Known Activations