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

    Neuronpedia

    INDEX
    Explanations

    empty input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posizione
    0.51
    觡
    0.47
    溌
    0.41
    觓
    0.41
    amanho
    0.40
    觛
    0.39
    ructive
    0.39
    xSpeed
    0.39
    pixels
    0.39
     സൃ
    0.39
    POSITIVE LOGITS
     alan
    0.38
     Tetra
    0.38
     children
    0.37
     ग्रेड
    0.36
     unconditional
    0.35
     LISA
    0.35
     Gent
    0.35
     Thr
    0.35
     tetra
    0.35
     ABC
    0.34
    Act Density 0.003%

    No Known Activations