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

    Neuronpedia

    INDEX
    Explanations

    getting lost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ới
    -0.07
     مهد
    -0.06
     yapan
    -0.06
    _To
    -0.06
     Дмит
    -0.06
     Billy
    -0.06
     Mart
    -0.06
    utsch
    -0.06
     Recipe
    -0.06
    主任
    -0.06
    POSITIVE LOGITS
    тех
    0.06
    ormap
    0.06
    μείο
    0.06
    reet
    0.06
    جن
    0.06
    .each
    0.06
    (abs
    0.06
    _FRONT
    0.06
     Fancy
    0.06
    .News
    0.06
    Act Density 0.009%

    No Known Activations