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

    Neuronpedia

    INDEX
    Explanations

    Code and configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дии
    -0.07
    Editing
    -0.06
    跨
    -0.06
    軍
    -0.06
    網
    -0.06
    [result
    -0.06
    并不
    -0.06
     Viewer
    -0.06
    军
    -0.06
     Modification
    -0.06
    POSITIVE LOGITS
     Exceptions
    0.07
    .Floor
    0.07
    교회
    0.06
    .match
    0.06
     czas
    0.06
     arrangements
    0.06
    غير
    0.06
    бра
    0.06
    .activities
    0.06
    .weight
    0.06
    Act Density 0.290%

    No Known Activations