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

    Neuronpedia

    INDEX
    Explanations

    landscapes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ừng
    -0.07
    我能
    -0.07
    iffany
    -0.07
    酺
    -0.07
    /native
    -0.07
     bụng
    -0.06
    untary
    -0.06
    atient
    -0.06
     raised
    -0.06
     הישראל
    -0.06
    POSITIVE LOGITS
    𝐊
    0.07
    كوك
    0.07
    Ｂ
    0.07
    Mor
    0.07
     zeal
    0.07
    <_
    0.07
    𝘬
    0.07
    _character
    0.07
    Fred
    0.07
    .preferences
    0.07
    Act Density 0.037%

    No Known Activations