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

    Neuronpedia

    INDEX
    Explanations

    state of being or motion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zusätz
    0.75
     результатом
    0.74
     grouping
    0.73
     తి
    0.73
    writelines
    0.72
     magma
    0.72
    অগ্র
    0.71
     część
    0.69
    result
    0.69
     ސ
    0.69
    POSITIVE LOGITS
    水平
    0.63
    లన
    0.60
     Stationary
    0.60
    ytics
    0.59
    ément
    0.58
     glaz
    0.58
     launched
    0.57
    launch
    0.56
    న్ను
    0.56
    꽝
    0.55
    Act Density 0.121%

    No Known Activations