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

    Neuronpedia

    INDEX
    Explanations

    connecting lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pptn
    0.38
    iggle
    0.37
    cloudflare
    0.36
     indef
    0.36
     sedent
    0.36
     cott
    0.36
    relsen
    0.35
     Vorg
    0.35
     singleRun
    0.35
    Ig
    0.35
    POSITIVE LOGITS
    ș
    0.48
     Authorities
    0.42
    ᱽ
    0.42
     अधिकारियों
    0.41
    romeda
    0.41
     authorities
    0.40
    してしまう
    0.38
    Authorities
    0.38
     статистики
    0.38
    ĭ
    0.38
    Act Density 0.000%

    No Known Activations