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

    Neuronpedia

    INDEX
    Explanations

    .version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    탄
    -0.07
    っ�
    -0.07
     disqualified
    -0.07
    살
    -0.07
    VAL
    -0.07
    ฟ
    -0.07
     contains
    -0.07
    皖
    -0.06
    🦔
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
    _ord
    0.07
     סביב
    0.07
    ㏂
    0.07
    機構
    0.07
     konuşma
    0.07
     stove
    0.06
    _sin
    0.06
    :k
    0.06
    _don
    0.06
    計畫
    0.06
    Act Density 0.002%

    No Known Activations