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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contexts in sentences

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

    siblings and family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.76
     चीज़ों
    -0.61
    новниш
    -0.57
    -0.57
    /**
    -0.53
     للاسماء
    -0.51
    /*
    -0.50
    parsedMessage
    -0.50
     CreateTagHelper
    -0.48
    awaiter
    -0.48
    POSITIVE LOGITS
     brothers
    0.56
     brother
    0.56
     sisters
    0.54
     sorella
    0.51
     uncles
    0.51
     kardeş
    0.50
     sister
    0.49
     Brother
    0.47
     frère
    0.47
    brother
    0.45
    Act Density 0.001%

    No Known Activations