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

    Neuronpedia

    INDEX
    Explanations

    makefiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ling
    -0.28
     mis
    -0.26
    IME
    -0.26
    emed
    -0.25
    é³³
    -0.25
     Said
    -0.25
    ạn
    -0.24
    工信éĥ¨
    -0.24
    ldr
    -0.24
    )|(
    -0.24
    POSITIVE LOGITS
     sacrificed
    0.29
    æ²½
    0.26
    Homepage
    0.25
    åѦåĪ°
    0.24
    åıij
    0.24
     Lessons
    0.24
    éĿ©
    0.24
    èĭĽ
    0.24
    oir
    0.23
    .character
    0.23
    Act Density 0.025%

    No Known Activations