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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or strong emotion

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

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.47
    resave
    -0.45
    postsleuth
    -0.42
    RequestQueue
    -0.41
    Autoritní
    -0.41
     colgante
    -0.40
     diſt
    -0.40
    mybatisplus
    -0.40
     disponibilités
    -0.39
    Bibliograf
    -0.39
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.54
    ChrTalk
    0.52
     defaultstate
    0.50
    sweet
    0.46
    unt
    0.44
    toxicity
    0.44
     Springfield
    0.41
    ⎨
    0.41
    UNUSED
    0.41
    \{\\
    0.41
    Act Density 0.046%

    No Known Activations