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

    Neuronpedia

    INDEX
    Explanations

    .TOTAL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pérdida
    0.27
     tzw
    0.25
    "+"|".
    0.25
     rám
    0.24
     wę
    0.24
    jeta
    0.24
     sữa
    0.24
    linkOpacity
    0.24
     struttura
    0.23
    पीरियंस
    0.23
    POSITIVE LOGITS
    6
    0.36
    ↵
    0.35
    7
    0.34
    ING
    0.33
    5
    0.33
    9
    0.33
     and
    0.33
    4
    0.33
    3
    0.33
    .
    0.32
    Act Density 0.074%

    No Known Activations