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

    Neuronpedia

    INDEX
    Explanations

    not needing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Г
    0.50
    И
    0.45
    К
    0.44
    G
    0.43
    \
    0.43
     \
    0.41
    ส
    0.40
    ฟ
    0.40
    Й
    0.39
    С
    0.39
    POSITIVE LOGITS
     Nhưng
    0.49
     normale
    0.45
     mantener
    0.44
     mindig
    0.44
     nhưng
    0.44
     sesu
    0.44
     mutta
    0.44
     mantenerse
    0.43
     cristiana
    0.42
     hardwoods
    0.42
    Act Density 0.002%

    No Known Activations