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

    Neuronpedia

    INDEX
    Explanations

    creators at google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    messages
    0.46
    жи
    0.44
    bonding
    0.39
    бай
    0.39
     messages
    0.38
    branding
    0.38
     создан
    0.38
    messaging
    0.37
    Hop
    0.37
     messaging
    0.37
    POSITIVE LOGITS
     Keyword
    0.55
    Keyword
    0.53
     keyword
    0.48
     goog
    0.48
    goog
    0.46
     Goog
    0.45
     google
    0.45
    キーワード
    0.44
     Sem
    0.42
    keyword
    0.42
    Act Density 0.028%

    No Known Activations