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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幾
    -0.08
     Sor
    -0.08
     mgr
    -0.08
     SAR
    -0.07
    房地产
    -0.07
     Vladimir
    -0.07
    遽
    -0.07
    Cor
    -0.07
     cosmic
    -0.07
     совсем
    -0.07
    POSITIVE LOGITS
    旯
    0.07
    OWN
    0.07
    izados
    0.06
    抡
    0.06
    一分钱
    0.06
    ꦗ
    0.06
    шу
    0.06
    �
    0.06
    SCREEN
    0.06
     downtown
    0.06
    Act Density 0.001%

    No Known Activations