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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to explanations and clarifications

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

    explaining or specifying context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chriſt
    -0.43
    الحياه
    -0.42
    ksom
    -0.40
     faſt
    -0.40
     cori
    -0.39
     Majefty
    -0.38
     calendriers
    -0.38
    canestro
    -0.38
     Arxivat
    -0.37
    absl
    -0.36
    POSITIVE LOGITS
    IVEREF
    0.53
    bootstrapcdn
    0.49
    yntaxException
    0.46
    tagext
    0.45
    PerformLayout
    0.45
    ってみました
    0.45
    TargetException
    0.44
     defaultstate
    0.44
    mtrl
    0.42
    cadilly
    0.42
    Act Density 0.049%

    No Known Activations