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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人在
    -0.08
     السابق
    -0.08
    Decorator
    -0.08
     debates
    -0.08
     देखकर
    -0.08
    Attr
    -0.07
     Agency
    -0.07
    Uma
    -0.07
    Shown
    -0.07
     reaj
    -0.07
    POSITIVE LOGITS
     basics
    0.09
     Basics
    0.08
     zunächst
    0.08
    -ish
    0.07
     ################################################
    0.07
     tín
    0.07
    信
    0.07
     Relevant
    0.07
    gb
    0.07
     ###↵
    0.07
    Act Density 0.056%

    No Known Activations