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

    Neuronpedia

    INDEX
    Explanations

    free tiers, blocking sites, war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हामी
    0.50
    อยู่ใน
    0.48
    鸳
    0.47
     йо
    0.46
     мы
    0.46
     aşağıdaki
    0.46
     ठिकाणी
    0.45
    нд
    0.45
     могут
    0.44
    読み
    0.44
    POSITIVE LOGITS
     Compute
    0.47
    Compute
    0.46
    ra
    0.44
     Gen
    0.43
     Themes
    0.43
     Inference
    0.43
     renal
    0.42
    Gen
    0.41
    '"
    0.41
     Concepts
    0.41
    Act Density 0.004%

    No Known Activations