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

    Neuronpedia

    INDEX
    Explanations

    virtual machines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ยนต
    -0.07
     ліс
    -0.07
    customer
    -0.07
    。不过
    -0.07
    丸
    -0.07
    .IsEnabled
    -0.07
    >())↵
    -0.06
     aircraft
    -0.06
     Intent
    -0.06
    โรงเร
    -0.06
    POSITIVE LOGITS
     operand
    0.06
    irse
    0.06
    _SEL
    0.06
    _RDONLY
    0.06
    .choice
    0.06
    ilation
    0.06
    687
    0.06
    -lat
    0.06
     WT
    0.06
    Profile
    0.06
    Act Density 0.031%

    No Known Activations