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

    Neuronpedia

    INDEX
    Explanations

    urls ending in `](`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.47
     is
    0.44
    ina
    0.39
     becomes
    0.36
     l
    0.35
     C
    0.34
    ian
    0.34
    ness
    0.32
     obscured
    0.32
     ณ
    0.32
    POSITIVE LOGITS
    ન
    0.50
    ون
    0.47
    ন
    0.43
    ر
    0.43
    이었
    0.42
    न
    0.40
    و
    0.40
    The
    0.39
    export
    0.38
    ແລະ
    0.38
    Act Density 0.650%

    No Known Activations