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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific code syntax elements

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

    option value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.51
    /**
    -0.47
    qJ
    -0.46
    matchCondition
    -0.45
    buttonShape
    -0.44
    fano
    -0.42
    fromnode
    -0.42
    RegressionTest
    -0.40
    Outros
    -0.40
     Forder
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.57
    出版年
    0.53
     ब्रेकडाउन
    0.52
    ConstraintMaker
    0.51
    Jereo
    0.49
     Мексичка
    0.47
    lwjgl
    0.46
    Cyfarwyddwr
    0.45
     مواليد
    0.45
     وتسجيلات
    0.44
    Act Density 0.007%

    No Known Activations