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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depart
    -0.07
    (tx
    -0.07
     drawer
    -0.07
    awaiter
    -0.07
    촣
    -0.06
     парти
    -0.06
    眇
    -0.06
     devoid
    -0.06
     callable
    -0.06
    ..."
    -0.06
    POSITIVE LOGITS
    ҹ
    0.07
    img
    0.07
    庚
    0.07
    썩
    0.07
    osta
    0.06
    缤纷
    0.06
    ización
    0.06
    position
    0.06
    轰炸
    0.06
    طار
    0.06
    Act Density 0.021%

    No Known Activations