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

    Neuronpedia

    INDEX
    Explanations

    questions and comments related to consumer experiences and recommendations

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

    common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cebo
    -0.38
     patrulla
    -0.38
     océano
    -0.36
    ControllerAdvice
    -0.36
     argint
    -0.36
     itulah
    -0.35
     stră
    -0.35
     Italij
    -0.35
     vuestros
    -0.35
     sustitu
    -0.34
    POSITIVE LOGITS
     resourceCulture
    0.78
     nakalista
    0.56
    tagext
    0.54
     gre
    0.49
     estekak
    0.49
     aDecoder
    0.49
    Hazards
    0.47
    뀜
    0.46
    MessageTagHelper
    0.45
    addGap
    0.45
    Act Density 0.112%

    No Known Activations