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

    Neuronpedia

    INDEX
    Explanations

    underrated label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或其他
    0.53
    或
    0.51
    ㎢
    0.46
     기반
    0.45
    に取り組
    0.44
    📄
    0.44
    🚆
    0.44
    ιών
    0.44
    तब
    0.44
    に変
    0.43
    POSITIVE LOGITS
     Praise
    0.57
     Viper
    0.54
     प्रशंसा
    0.53
     After
    0.52
     Lihat
    0.50
     Veterinary
    0.50
     Nuggets
    0.50
     Tristan
    0.50
     Google
    0.49
     Fans
    0.48
    Act Density 0.018%

    No Known Activations