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

    Neuronpedia

    INDEX
    Explanations

    impact and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کبھی
    0.55
    总是
    0.48
     mindig
    0.47
     কখনই
    0.47
     selalu
    0.46
     कभी
    0.45
     Lately
    0.45
     دائما
    0.45
    越来越
    0.45
     lately
    0.44
    POSITIVE LOGITS
     affected
    1.33
    affected
    1.30
     impacted
    1.17
     Affected
    1.15
     betroffen
    1.13
    Affected
    1.11
     afectados
    1.09
     repercussions
    1.08
     implications
    1.04
     afectado
    1.04
    Act Density 0.018%

    No Known Activations