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

    Neuronpedia

    INDEX
    Explanations

    responses related to grading and evaluation

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

    grading and correctness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     token
    -0.34
    Général
    -0.31
    gatsby
    -0.29
    token
    -0.29
    permitAll
    -0.28
    رشف
    -0.28
    ν
    -0.27
     beng
    -0.26
    Tage
    -0.26
    ่าว
    -0.25
    POSITIVE LOGITS
    TagMode
    0.68
    oredCriteria
    0.66
     kasarigan
    0.65
    0.62
     Administrativna
    0.62
    fjspx
    0.60
    답
    0.60
     disambiguazione
    0.60
     increí
    0.59
    grader
    0.57
    Act Density 0.287%

    No Known Activations