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

    Neuronpedia

    INDEX
    Explanations

    rankings or numerical ratings of entities

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

    ranking or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ยนต์
    -0.38
     and
    -0.33
    ,
    -0.32
     murni
    -0.32
    wnież
    -0.28
    ฟัง
    -0.28
    and
    -0.28
     einf
    -0.28
     quizás
    -0.27
    combined
    -0.26
    POSITIVE LOGITS
    ConstraintMaker
    1.02
     Nummer
    0.82
    №
    0.81
     houſe
    0.80
     NUMBER
    0.79
     №
    0.76
     queſta
    0.75
     nummer
    0.73
     number
    0.73
     RANK
    0.73
    Act Density 0.015%

    No Known Activations