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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics in research

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

    digits followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.75
     GenerationType
    -0.73
    iſen
    -0.73
    ðsíða
    -0.72
    ſelf
    -0.71
    AxisAlignment
    -0.71
     surla
    -0.69
    niſſe
    -0.68
     myſelf
    -0.67
    iſten
    -0.66
    POSITIVE LOGITS
    LabelTagHelper
    0.40
    şak
    0.32
     Schwier
    0.30
    def
    0.29
     Berger
    0.26
     treo
    0.26
     kaarangay
    0.26
     Viertel
    0.25
    рей
    0.25
    Verkehr
    0.25
    Act Density 0.132%

    No Known Activations