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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    064
    -0.08
    знач
    -0.07
     꽃
    -0.06
     为
    -0.06
    çı
    -0.06
     beberapa
    -0.06
    둘
    -0.06
    <Cell
    -0.06
     повідом
    -0.06
    ican
    -0.06
    POSITIVE LOGITS
    deal
    0.07
    -finals
    0.06
    Mp
    0.06
    ائج
    0.06
    ampler
    0.06
    μει
    0.06
    chten
    0.06
    ogy
    0.06
    uyệ
    0.06
    ρε
    0.05
    Act Density 0.060%

    No Known Activations