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

    Neuronpedia

    INDEX
    Explanations

    half-elf, half-orc, halfling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     więc
    0.51
     weiterhin
    0.50
     sehingga
    0.49
     votre
    0.45
     પૂર્ણ
    0.44
     nella
    0.44
     takže
    0.44
     vostra
    0.43
     τότε
    0.43
     untuk
    0.43
    POSITIVE LOGITS
    കം
    0.44
    Apple
    0.41
    アイ
    0.39
    Afghan
    0.39
    爱
    0.39
    Already
    0.39
    但不
    0.39
    Arabic
    0.39
    iciary
    0.38
    никами
    0.38
    Act Density 0.093%

    No Known Activations