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

    Neuronpedia

    INDEX
    Explanations

    coc-ada

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demokrat
    0.84
     deviant
    0.84
     wobec
    0.80
    ivism
    0.79
     społecz
    0.75
     πολι
    0.74
     audiovis
    0.74
     визна
    0.73
    minded
    0.72
     Confucian
    0.72
    POSITIVE LOGITS
     الماء
    1.23
     خشک
    1.04
    blätter
    1.00
    干燥
    0.97
     poquito
    0.96
     bottles
    0.96
     ውሃ
    0.95
    நீர்
    0.94
     glowing
    0.94
     dedos
    0.93
    Act Density 0.143%

    No Known Activations