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

    Neuronpedia

    INDEX
    Explanations

    specifications and required components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ik
    1.13
    ile
    1.01
    zie
    0.99
     or
    0.98
     τις
    0.98
    isan
    0.96
    이나
    0.95
    ere
    0.91
    ast
    0.91
    alle
    0.91
    POSITIVE LOGITS
     bawang
    0.70
     serangan
    0.68
     Tetapi
    0.67
     하지만
    0.66
     زیرا
    0.66
     қа
    0.66
     Seperti
    0.66
    ഒ
    0.66
     dosta
    0.65
    ZUKI
    0.64
    Act Density 0.274%

    No Known Activations