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

    Neuronpedia

    INDEX
    Explanations

    references to programming and technical concepts

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

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.51
    Vidite
    -0.47
    gebnis
    -0.46
     Beauchamp
    -0.46
    @__
    -0.46
    endregion
    -0.45
     intptr
    -0.45
    ↵↵↵
    -0.44
    épendance
    -0.43
    @^
    -0.43
    POSITIVE LOGITS
     Bewußt
    0.48
     pouvoit
    0.46
    optionalTypeArgs
    0.45
    이션
    0.43
     auroit
    0.43
     utafitiHapana
    0.42
     asisti
    0.42
     griech
    0.41
    verwijspagina
    0.40
     يتيمه
    0.40
    Act Density 0.242%

    No Known Activations