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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and quantities in a scientific or technical context

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

    mg, ml, numbers, versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.64
    +#+
    -0.63
    帖最后由
    -0.59
    #+#
    -0.58
    DebuggerStep
    -0.56
    ðsíða
    -0.56
    Eloquent
    -0.56
    sizeCache
    -0.56
     ModelRenderer
    -0.55
    +#+#
    -0.54
    POSITIVE LOGITS
    entuh
    0.32
    zule
    0.27
    ionine
    0.26
     mellett
    0.26
    bite
    0.26
    laught
    0.25
     sezonu
    0.25
    uttosto
    0.24
    ITIS
    0.24
     Schicht
    0.24
    Act Density 0.139%

    No Known Activations