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

    Neuronpedia

    INDEX
    Explanations

    Stream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    产
    -0.08
    色
    -0.08
     Plus
    -0.08
     intellig
    -0.08
    亮
    -0.08
    PLUS
    -0.08
     deut
    -0.07
    Plus
    -0.07
     Helic
    -0.07
     conversations
    -0.07
    POSITIVE LOGITS
     वा
    0.09
     FV
    0.08
     opst
    0.08
     FL
    0.08
     installs
    0.08
     इंस्ट
    0.08
     fechado
    0.08
     बां
    0.08
     सहायता
    0.08
     wo
    0.08
    Act Density 0.003%

    No Known Activations