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

    Neuronpedia

    INDEX
    Explanations

    great depth and detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reaffirmed
    0.90
     effiz
    0.78
     affirmed
    0.76
     pelaksanaan
    0.75
    সাল
    0.75
     strument
    0.74
     correttamente
    0.73
     windscreen
    0.73
     nonconvex
    0.73
     acknowledgment
    0.73
    POSITIVE LOGITS
     great
    0.95
    great
    0.90
     Great
    0.84
    Great
    0.84
     depth
    0.83
    depth
    0.81
    Depth
    0.79
     length
    0.73
    length
    0.73
     Depth
    0.72
    Act Density 0.077%

    No Known Activations