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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and interrogative phrases

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

    questions and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.65
    AddTagHelper
    -0.62
    BufferException
    -0.56
    󠁿
    -0.56
     gyhoeddwyd
    -0.55
     fubject
    -0.54
    MemoryWarning
    -0.54
     indígen
    -0.52
    soever
    -0.51
    GTCX
    -0.51
    POSITIVE LOGITS
     A
    0.39
     considérons
    0.35
     The
    0.35
     wiecz
    0.35
    RegressionTest
    0.35
     mów
    0.34
     New
    0.34
     omge
    0.34
    A
    0.34
    The
    0.33
    Act Density 0.004%

    No Known Activations