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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     احتم
    -0.06
     Kumar
    -0.06
     Haven
    -0.06
     Protestant
    -0.06
    _markers
    -0.06
     für
    -0.06
     exceptions
    -0.06
    ;!
    -0.06
    Planning
    -0.06
     Privacy
    -0.06
    POSITIVE LOGITS
     NZ
    0.07
    غراف
    0.06
    $results
    0.06
    .retry
    0.06
     Kinder
    0.06
    (argument
    0.06
     (_,
    0.06
    рій
    0.06
    iju
    0.06
     Meanwhile
    0.06
    Act Density 0.015%

    No Known Activations