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

    Neuronpedia

    INDEX
    Explanations

    low quality text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .jms
    -0.07
    moved
    -0.06
     Estr
    -0.06
    /package
    -0.06
    ito
    -0.06
    <User
    -0.06
     cabins
    -0.06
     Serum
    -0.06
    ourcem
    -0.06
    .herokuapp
    -0.06
    POSITIVE LOGITS
     Screens
    0.07
     effortlessly
    0.07
     работа
    0.07
     그래
    0.07
     preparations
    0.07
     віднос
    0.07
    -generic
    0.06
     ekonom
    0.06
    Multiplier
    0.06
    目标
    0.06
    Act Density 0.119%

    No Known Activations