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

    Neuronpedia

    INDEX
    Explanations

    instances of structured or formatted textual elements

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

    foreign months and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bibliografie
    -0.47
     controlada
    -0.46
     duradero
    -0.45
     interactiva
    -0.43
     contemporánea
    -0.41
     compuesta
    -0.40
     peligroso
    -0.40
     gruesa
    -0.40
     judiciaire
    -0.39
     confiable
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    0.80
    rungsseite
    0.73
    anguages
    0.69
     BoxFit
    0.66
    InputBorder
    0.64
     للمعارف
    0.63
     ſind
    0.60
    ՚
    0.60
    inWeight
    0.60
    ⟬
    0.58
    Act Density 0.026%

    No Known Activations