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

    Neuronpedia

    INDEX
    Explanations

    definitions and discussions about understanding and measurement in various contexts

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

    depends on success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.48
    moveToFirst
    -0.47
    AndEndTag
    -0.44
    writeFieldEnd
    -0.44
    ToBounds
    -0.43
    /*
    -0.42
    ArrowToggle
    -0.40
    WireFormat
    -0.40
    InjectMocks
    -0.40
    Hentet
    -0.39
    POSITIVE LOGITS
     başar
    0.50
     succès
    0.48
     successo
    0.45
     Entste
    0.43
    success
    0.43
     sucesso
    0.43
     affari
    0.43
    må
    0.42
     externi
    0.42
     Herkunft
    0.42
    Act Density 0.260%

    No Known Activations