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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afe
    -0.07
     yapıl
    -0.07
    .readlines
    -0.07
     jurisdiction
    -0.06
     //
    -0.06
    kte
    -0.06
    Когда
    -0.06
    tables
    -0.06
    bringing
    -0.06
    (location
    -0.06
    POSITIVE LOGITS
    arer
    0.07
     ELECT
    0.07
    -range
    0.06
    (',
    0.06
     Portuguese
    0.06
    CppMethodPointer
    0.06
     lament
    0.06
    <usize
    0.06
     eru
    0.06
     acab
    0.06
    Act Density 0.034%

    No Known Activations