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

    Neuronpedia

    INDEX
    Explanations

    assert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivate
    -0.06
    .indent
    -0.06
     Brushes
    -0.06
     seeding
    -0.06
    壓
    -0.06
    .dir
    -0.06
    modified
    -0.06
     Autof
    -0.06
     kuvvet
    -0.06
    maint
    -0.06
    POSITIVE LOGITS
     знову
    0.07
    /ms
    0.07
    (nodes
    0.06
    ";}↵
    0.06
    ako
    0.06
    ’ı
    0.06
     zal
    0.06
    !';↵
    0.06
     Denied
    0.06
     kurtar
    0.06
    Act Density 0.003%

    No Known Activations