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

    Neuronpedia

    INDEX
    Explanations

    pressure cooker safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WWW
    -0.09
     mow
    -0.09
    llllllll
    -0.09
     melody
    -0.08
     pedestrian
    -0.08
     desemp
    -0.08
    兼职
    -0.08
    Fond
    -0.08
     mian
    -0.08
     uta
    -0.08
    POSITIVE LOGITS
     নিরাপ
    0.10
     safety
    0.10
     steam
    0.09
    Safety
    0.09
    安全
    0.09
     boilers
    0.09
     Safety
    0.09
    .exceptions
    0.09
     armored
    0.08
     ciphertext
    0.08
    Act Density 0.016%

    No Known Activations