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

    Neuronpedia

    INDEX
    Explanations

    closing braces and function declarations in code

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

    code and programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.53
    MessageOf
    -0.51
    EndInit
    -0.46
     InputDecoration
    -0.43
     ویکی‌پدی
    -0.41
    Personendaten
    -0.41
    ResumeLayout
    -0.38
     autorytatywna
    -0.37
     通販
    -0.36
     <>",
    -0.35
    POSITIVE LOGITS
    ragma
    0.49
    RegressionTest
    0.47
    **
    0.47
     الحره
    0.45
     /**
    0.45
    ullan
    0.44
     isolada
    0.43
     خاطر
    0.43
     hinweg
    0.43
     ‎
    0.42
    Act Density 0.006%

    No Known Activations