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

    Neuronpedia

    INDEX
    Explanations

    Q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     containing
    -0.07
    elve
    -0.07
    iais
    -0.07
     взрос
    -0.06
     victorious
    -0.06
     lugar
    -0.06
    allocator
    -0.06
    allis
    -0.06
    박
    -0.06
    cms
    -0.06
    POSITIVE LOGITS
    Recently
    0.06
     Modifier
    0.06
    Exercise
    0.06
    -remove
    0.06
    ไทย
    0.06
     son
    0.06
    .shutdown
    0.06
    '>
    0.06
    )tableView
    0.06
     evenings
    0.05
    Act Density 0.003%

    No Known Activations