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

    Neuronpedia

    INDEX
    Explanations

    references to specific file paths and locations in documents

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

    links or URLs, code, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vuestros
    -0.33
    guenos
    -0.33
     étoient
    -0.31
     femenino
    -0.30
     gobier
    -0.30
     appétit
    -0.29
     emprego
    -0.29
     vuestro
    -0.29
     Erhaltung
    -0.29
    ถม
    -0.28
    POSITIVE LOGITS
    ValueStyle
    0.88
    rungsseite
    0.87
    WriteBarrier
    0.86
     MainAxisSize
    0.85
    findpost
    0.85
    MemoryWarning
    0.83
    RectangleBorder
    0.79
    WriteTagHelper
    0.79
    RTLR
    0.76
    esez
    0.75
    Act Density 0.025%

    No Known Activations