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

    Neuronpedia

    INDEX
    Explanations

    carefully removing or fixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    レート
    0.43
    fitting
    0.43
    getting
    0.41
     customs
    0.40
    apt
    0.39
     fitting
    0.39
    ath
    0.38
    ajes
    0.37
    att
    0.37
    art
    0.36
    POSITIVE LOGITS
     Yeşil
    0.49
     mest
    0.43
     atualização
    0.43
     activación
    0.43
    ﮯ
    0.43
     Ç
    0.43
     verdade
    0.43
     privacidad
    0.43
     cfr
    0.42
     privacidade
    0.42
    Act Density 0.001%

    No Known Activations