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

    Neuronpedia

    INDEX
    Explanations

    code, scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awake
    -0.07
     reconsider
    -0.07
     fairly
    -0.06
     обесп
    -0.06
     breathing
    -0.06
     hemos
    -0.06
     Reflection
    -0.06
     reproduction
    -0.06
     Heritage
    -0.06
     Flower
    -0.06
    POSITIVE LOGITS
    ("\
    0.06
    frag
    0.06
     mutations
    0.06
    。“
    0.06
    .FileReader
    0.06
     edil
    0.06
    _sur
    0.06
     în
    0.06
    .Per
    0.06
    .Completed
    0.06
    Act Density 0.000%

    No Known Activations