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

    Neuronpedia

    INDEX
    Explanations

    Code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Retrieve
    -0.07
     Florian
    -0.06
     flies
    -0.06
     держав
    -0.06
    "For
    -0.06
     asteroids
    -0.06
     ↵		↵
    -0.06
    Coding
    -0.06
     hemat
    -0.06
     NHS
    -0.06
    POSITIVE LOGITS
     stutter
    0.07
    Construct
    0.07
    ยะ
    0.06
     ナ
    0.06
     yapıl
    0.06
    ��态
    0.06
    游戏
    0.06
     Prague
    0.06
    .Down
    0.06
    isz
    0.06
    Act Density 0.001%

    No Known Activations