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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pablo
    -0.07
     semen
    -0.07
     І
    -0.06
    В
    -0.06
    一起
    -0.06
     timer
    -0.06
    tip
    -0.06
    iolet
    -0.06
     تک
    -0.06
    Hit
    -0.06
    POSITIVE LOGITS
    defaults
    0.07
    ength
    0.07
    nesota
    0.07
    reply
    0.06
    valuator
    0.06
    ？」↵↵
    0.06
    ńst
    0.06
    firm
    0.06
    cales
    0.06
    zc
    0.06
    Act Density 0.005%

    No Known Activations