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

    Neuronpedia

    INDEX
    Explanations

    explain this quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рано
    0.47
    nahi
    0.46
     خاص
    0.46
    ndown
    0.45
    ଃ
    0.45
     whining
    0.44
    ULTY
    0.44
    न्दु
    0.43
     uninformed
    0.42
    Complaint
    0.42
    POSITIVE LOGITS
     Jobs
    0.46
     McIl
    0.45
     Te
    0.45
    Между
    0.44
    พล
    0.44
    โ
    0.44
     Countries
    0.43
     Soho
    0.43
     V
    0.43
     _,
    0.43
    Act Density 0.000%

    No Known Activations