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

    Neuronpedia

    INDEX
    Explanations

    specific symbols and formatting used in mathematical or technical notation

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

    special characters in code or math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はじめに
    -0.48
    findpost
    -0.46
    Autoritní
    -0.44
     snippetHide
    -0.37
     skimage
    -0.35
     resourceCulture
    -0.34
     propOrder
    -0.34
    Geplaatst
    -0.33
     []:
    -0.32
    TagHelper
    -0.32
    POSITIVE LOGITS
    mpo
    0.57
    zino
    0.52
    tilor
    0.51
    astify
    0.51
     direta
    0.50
    ⟬
    0.50
    polazione
    0.50
    topes
    0.49
    ginous
    0.49
    rhos
    0.48
    Act Density 0.170%

    No Known Activations