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

    Neuronpedia

    INDEX
    Explanations

    including

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fa
    -0.07
     Wild
    -0.07
     오
    -0.06
     Joe
    -0.06
    .js
    -0.06
    三三
    -0.06
     Laguna
    -0.06
    ῖ
    -0.06
     �
    -0.06
    .Fore
    -0.06
    POSITIVE LOGITS
     INCLUDING
    0.09
     including
    0.07
     joints
    0.07
     chiếm
    0.06
    including
    0.06
    —including
    0.06
     surrounding
    0.06
    ảng
    0.06
     перел
    0.06
     могли
    0.06
    Act Density 0.035%

    No Known Activations