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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming components or libraries

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

    user inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.50
     gezet
    -0.49
     beroep
    -0.49
    jména
    -0.48
    Autoritní
    -0.47
     behulp
    -0.47
    قایناقلار
    -0.46
     TextAppearance
    -0.46
     provecho
    -0.45
     tarvit
    -0.44
    POSITIVE LOGITS
    ↗
    0.57
    ffine
    0.49
    flexGrow
    0.47
     sympy
    0.47
    phosa
    0.46
    TempData
    0.44
    AnchorStyles
    0.44
    tvguidetime
    0.44
    ssymb
    0.42
    gameserver
    0.42
    Act Density 0.009%

    No Known Activations