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

    Neuronpedia

    INDEX
    Explanations

    membranes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hop
    -0.07
     blí
    -0.07
    泊
    -0.07
    .Convert
    -0.07
    Wave
    -0.07
    (sel
    -0.06
    _pot
    -0.06
     못
    -0.06
     deliberately
    -0.06
    Matcher
    -0.06
    POSITIVE LOGITS
     제목
    0.07
     Thinking
    0.06
     MSC
    0.06
    ayacak
    0.06
    andum
    0.06
    atient
    0.06
     loads
    0.06
     actor
    0.06
     فرمان
    0.06
    rieg
    0.06
    Act Density 0.040%

    No Known Activations