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

    Neuronpedia

    INDEX
    Explanations

    video game combat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atched
    -0.08
     �
    -0.07
     Jonah
    -0.07
    orpion
    -0.07
    岌
    -0.07
    ştır
    -0.07
    ข
    -0.07
     tts
    -0.06
    โห
    -0.06
     poisoning
    -0.06
    POSITIVE LOGITS
    那儿
    0.07
     zamówienia
    0.07
     миллион
    0.07
     pamięta
    0.07
     Lynn
    0.07
    哪家好
    0.07
    >())
    0.07
    润滑
    0.07
    _arguments
    0.07
     helping
    0.07
    Act Density 0.060%

    No Known Activations