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

    Neuronpedia

    INDEX
    Explanations

    help you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ガ
    0.39
    ern
    0.39
     항상
    0.39
     보
    0.39
    itoria
    0.39
     oneness
    0.39
     optimum
    0.38
     fullness
    0.38
    icot
    0.38
     correctness
    0.37
    POSITIVE LOGITS
    ങ്കിലും
    0.47
    或
    0.46
    نوان
    0.46
    প্রচার
    0.45
     અથવા
    0.43
    TextureAsset
    0.43
     суда
    0.43
     или
    0.42
    دهم
    0.42
    🈷
    0.42
    Act Density 0.006%

    No Known Activations