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

    Neuronpedia

    INDEX
    Explanations

    classic riddles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.49
    u
    0.46
    ↵
    0.44
     Suitable
    0.42
    valence
    0.41
    x
    0.41
     Valencia
    0.40
    ill
    0.40
     \\
    0.40
     Scheduled
    0.40
    POSITIVE LOGITS
    唥
    0.56
    オブ
    0.50
    ტიკ
    0.49
    ்க
    0.48
     செயல
    0.47
    -->'
    0.47
     ஆட
    0.46
    𒀊
    0.46
    lexeme
    0.46
     ovipares
    0.46
    Act Density 0.003%

    No Known Activations