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

    Neuronpedia

    INDEX
    Explanations

    ips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     च
    -0.07
    紹
    -0.06
    ('_',
    -0.06
    gre
    -0.06
     rud
    -0.06
    گانی
    -0.06
    (mac
    -0.06
     quat
    -0.05
    _ud
    -0.05
     Ром
    -0.05
    POSITIVE LOGITS
     Initialise
    0.08
     Dump
    0.07
    жа
    0.07
    ################################
    0.07
    .assertIn
    0.07
     Inter
    0.07
     Jerusalem
    0.07
     него
    0.06
    ्म
    0.06
     HOME
    0.06
    Act Density 0.000%

    No Known Activations