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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references to web resources or documentation

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

    URLs for documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.48
     leſs
    -0.40
     uſed
    -0.40
     purpoſe
    -0.40
     chofe
    -0.39
    chappement
    -0.39
     Monfieur
    -0.39
     diſt
    -0.38
     ſta
    -0.37
     anſ
    -0.37
    POSITIVE LOGITS
     '\\;'
    0.63
    providedIn
    0.59
    UserScript
    0.53
    styleable
    0.52
    thâu
    0.52
     transférez
    0.50
     betweenstory
    0.50
    __':
    0.49
     TableColumn
    0.48
    Rüyada
    0.48
    Act Density 0.067%

    No Known Activations