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

    Neuronpedia

    INDEX
    Explanations

    technical terms and definitions related to mathematical and scientific concepts

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

    describes existing states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.41
     apapun
    -0.37
    tagHelperRunner
    -0.36
     nachher
    -0.36
     siihen
    -0.36
    MessageTagHelper
    -0.36
     senare
    -0.36
     skolan
    -0.35
     manchmal
    -0.35
     relâche
    -0.35
    POSITIVE LOGITS
    uxxxx
    0.56
     ſei
    0.48
    remont
    0.47
     ſind
    0.47
     Administrativna
    0.46
    CloseOperation
    0.46
    Cata
    0.46
     queſta
    0.46
    oporosis
    0.45
    gau
    0.45
    Act Density 0.068%

    No Known Activations