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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and relationships in discussions related to performance, outcomes, or measurements

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

    `molecular patterns`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.37
     Roskov
    -0.37
     riêng
    -0.36
    Сам
    -0.35
    lně
    -0.35
     Kasper
    -0.35
     Schwier
    -0.35
     that
    -0.35
     diría
    -0.35
    STE
    -0.34
    POSITIVE LOGITS
     nakalista
    0.57
    0.56
    Capítulo
    0.53
     noDo
    0.53
    تقاوى
    0.52
    bewerken
    0.51
     Мексичка
    0.51
    Demografie
    0.50
    ValueStyle
    0.50
    󠁣
    0.49
    Act Density 0.075%

    No Known Activations