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

    Neuronpedia

    INDEX
    Explanations

    programming data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     суть
    0.54
    ili
    0.52
    ama
    0.52
    ah
    0.51
    ian
    0.49
    кина
    0.45
     когда
    0.44
    廪
    0.44
    ya
    0.44
    🌘
    0.43
    POSITIVE LOGITS
     of
    0.95
     Of
    0.73
    Of
    0.68
     ഓഫ്
    0.62
    of
    0.62
     ofthe
    0.60
    sof
    0.59
     containing
    0.57
    OfString
    0.55
     OF
    0.53
    Act Density 0.052%

    No Known Activations