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

    Neuronpedia

    INDEX
    Explanations

    questions and comparisons relating to numerical values or quantities

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

    I have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.43
     darte
    -0.33
     tege
    -0.32
    endurch
    -0.32
     toch
    -0.32
     pengh
    -0.31
    medriver
    -0.31
     مط
    -0.31
    diert
    -0.31
    retweeted
    -0.31
    POSITIVE LOGITS
     Autorizaciones
    0.62
    Datuak
    0.60
     ſind
    0.59
    __":
    0.57
    حياته
    0.56
     Autorisations
    0.56
     Jefus
    0.56
    حياتها
    0.54
     ſy
    0.54
    RotationOrder
    0.53
    Act Density 0.076%

    No Known Activations