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

    Neuronpedia

    INDEX
    Explanations

    references to political corruption and financial misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    financial transactions and denials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuning
    -0.30
    體驗
    -0.29
     amada
    -0.28
    ureusement
    -0.28
     médecine
    -0.27
     putty
    -0.27
     Ense
    -0.27
     Experience
    -0.27
     tuning
    -0.26
    unikasi
    -0.26
    POSITIVE LOGITS
    ScopeManager
    0.64
    SharedDtor
    0.63
     estekak
    0.57
    AutoField
    0.55
    تقاوى
    0.55
     ویکی‌پدی
    0.54
    concern
    0.53
     متعلقه
    0.52
    MLLoader
    0.52
    principalColumn
    0.51
    Act Density 0.057%

    No Known Activations