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

    Neuronpedia

    INDEX
    Explanations

    terms related to background elements and definitions within various contexts

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

    background, Freedom, Proof, Specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -1.46
    ítmény
    -0.80
    enskap
    -0.73
    𝓴
    -0.63
    𝓫
    -0.62
    isa
    -0.60
    𝓭
    -0.60
    𝓹
    -0.59
    çası
    -0.57
    𝓵
    -0.57
    POSITIVE LOGITS
    s
    1.06
    ième
    0.71
    ים
    0.66
    sweise
    0.64
    ς
    0.61
     EconPapers
    0.61
     sánchez
    0.60
     يتيمه
    0.59
     garcía
    0.58
    bidities
    0.58
    Act Density 0.077%

    No Known Activations