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

    Neuronpedia

    INDEX
    Explanations

    quotes and sayings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Videos
    0.44
    curl
    0.43
    videos
    0.42
    topics
    0.41
    stuff
    0.40
     videos
    0.39
    logs
    0.38
     Slo
    0.38
    フェア
    0.37
    respectively
    0.37
    POSITIVE LOGITS
     quote
    0.49
    这句话
    0.49
     Anonymous
    0.44
     rozm
    0.43
    这话
    0.42
     কথাটা
    0.42
     paraphrase
    0.42
     이라고
    0.41
     anonymous
    0.41
     कहकर
    0.41
    Act Density 0.136%

    No Known Activations