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

    Neuronpedia

    INDEX
    Explanations

    general followed by assembly, liability, instructions, counsel, ledger, kenobi, repository, manager, language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teilen
    0.44
    ං
    0.40
     nejen
    0.39
     energi
    0.38
    நுட்ப
    0.38
     zmienia
    0.38
     privata
    0.38
     فرص
    0.38
    专注于
    0.37
     chunkSize
    0.37
    POSITIVE LOGITS
     general
    1.53
    general
    1.38
     général
    1.33
    General
    1.32
    GENERAL
    1.25
     GENERAL
    1.23
     General
    1.19
     generales
    1.16
     generale
    1.13
     générale
    1.12
    Act Density 0.026%

    No Known Activations