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

    Neuronpedia

    INDEX
    Explanations

    favorites and possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pant
    -0.07
     escalate
    -0.06
    萹
    -0.06
    الي
    -0.06
     encode
    -0.06
    explained
    -0.06
     nhất
    -0.06
    话语
    -0.06
    人民银行
    -0.06
    דתי
    -0.06
    POSITIVE LOGITS
    >f
    0.08
     UTC
    0.07
    TLS
    0.07
     שימוש
    0.07
    衷心
    0.07
    |RF
    0.07
     LeBron
    0.07
     darf
    0.07
    ຣ
    0.07
    תרבות
    0.06
    Act Density 0.005%

    No Known Activations