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

    Neuronpedia

    INDEX
    Explanations

    stack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SetUp
    -0.08
     سر
    -0.07
    arging
    -0.07
     на
    -0.07
     "-"↵
    -0.07
    .white
    -0.06
     auf
    -0.06
     σύ
    -0.06
     Sin
    -0.06
    _that
    -0.06
    POSITIVE LOGITS
    uesday
    0.07
    HT
    0.07
     layoffs
    0.06
    ınıza
    0.06
    ammable
    0.06
    ham
    0.06
    _soc
    0.06
     stacks
    0.06
     صنایع
    0.06
    Dependency
    0.06
    Act Density 0.006%

    No Known Activations