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

    Neuronpedia

    INDEX
    Explanations

    structural elements and formatting in data representation

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

    structured data keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.51
    UnusedPrivate
    -0.47
    ioutil
    -0.47
    setVerticalGroup
    -0.43
     zijne
    -0.43
    fromnode
    -0.41
    LookAnd
    -0.41
     diſt
    -0.41
     dAtA
    -0.40
     tranſ
    -0.40
    POSITIVE LOGITS
    исленность
    0.49
     Meksiku
    0.46
    tique
    0.44
    ">—
    0.43
    ArrowToggle
    0.42
     nakalista
    0.42
     ?>>
    0.41
    kasten
    0.41
     Spass
    0.40
    mety
    0.39
    Act Density 0.007%

    No Known Activations