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

    Neuronpedia

    INDEX
    Explanations

    movie/show plot descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     คำ
    -0.08
     Oxford
    -0.07
     Odin
    -0.06
    لمة
    -0.06
    tour
    -0.06
    -around
    -0.06
    CLASS
    -0.06
    ařilo
    -0.06
     Jerry
    -0.06
    ellij
    -0.06
    POSITIVE LOGITS
     passer
    0.07
     PRICE
    0.07
    _wrapper
    0.06
     pense
    0.06
    怪
    0.06
     favor
    0.06
    _gift
    0.06
     süt
    0.06
    .water
    0.06
     pris
    0.06
    Act Density 0.055%

    No Known Activations