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

    Neuronpedia

    INDEX
    Explanations

    Command line and package management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    只不过
    -0.07
    עצב
    -0.07
    (generator
    -0.06
    _ATTRIBUTES
    -0.06
     treasurer
    -0.06
    .toFloat
    -0.06
    .SubItems
    -0.06
     els
    -0.06
    挥手
    -0.06
     şöyle
    -0.06
    POSITIVE LOGITS
    案
    0.07
    ič
    0.07
    اق
    0.07
    ....↵
    0.07
    诣
    0.07
     discuss
    0.06
     classified
    0.06
    該
    0.06
    反对
    0.06
     NYC
    0.06
    Act Density 0.028%

    No Known Activations