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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

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

    Fractions and basic arithmetic

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.65
    balleur
    -0.60
     (!_
    -0.59
     saites
    -0.57
    XmlAccessType
    -0.56
     !_
    -0.54
    ştır
    -0.53
     Exacts
    -0.53
     delta
    -0.51
     Beta
    -0.51
    POSITIVE LOGITS
    cancel
    0.71
     poichè
    0.61
     hänen
    0.61
     quæ
    0.61
    underbrace
    0.59
    Gizmos
    0.56
     aikana
    0.55
     isolado
    0.54
     colorés
    0.54
     feroit
    0.54
    Act Density 1.114%

    No Known Activations