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

    Neuronpedia

    INDEX
    Explanations

    conditional and causal phrases indicating relationships between concepts or actions

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

    prepositions and conjunctions followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.60
    EndInit
    -0.52
     contextLoads
    -0.52
    BASEPATH
    -0.52
     queſto
    -0.51
     delimiter
    -0.49
     للمعارف
    -0.49
    +#+
    -0.48
     florida
    -0.47
    Біо
    -0.47
    POSITIVE LOGITS
     تضيفلها
    0.56
     surla
    0.46
    ⎩
    0.43
     Pflanze
    0.38
     kés
    0.35
    uidado
    0.35
     setengah
    0.33
     kemeja
    0.32
    VIAF
    0.32
     suela
    0.32
    Act Density 0.383%

    No Known Activations