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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or parameters

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

    answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ichio
    -0.52
    <bos>
    -0.51
    Välislingid
    -0.48
    miljø
    -0.44
    ::::::::::::::::
    -0.44
    ítmény
    -0.42
     Cune
    -0.42
     murni
    -0.42
     besky
    -0.41
     nedeniyle
    -0.40
    POSITIVE LOGITS
     ans
    2.28
    Ans
    0.88
     Ans
    0.83
     anse
    0.80
     ANS
    0.72
     Anson
    0.67
     ANSWERS
    0.63
     answer
    0.61
     anf
    0.60
     Answers
    0.59
    Act Density 0.001%

    No Known Activations