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

    Neuronpedia

    INDEX
    Explanations

    defender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reform
    -0.07
     ammunition
    -0.07
     europ
    -0.07
    iversite
    -0.07
     powers
    -0.06
    acity
    -0.06
    کور
    -0.06
     europe
    -0.06
    gypt
    -0.06
     guiding
    -0.06
    POSITIVE LOGITS
    ・━
    0.08
     Defender
    0.07
     defenders
    0.06
    _redirected
    0.06
    ู
    0.06
    $$
    0.06
    .setModel
    0.06
    .deepEqual
    0.06
    0.06
    iễ
    0.06
    Act Density 0.001%

    No Known Activations