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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bö
    -0.07
    ñe
    -0.07
    -stock
    -0.07
    塞尔
    -0.07
    cadena
    -0.07
    绿色
    -0.07
    房车
    -0.07
    (any
    -0.06
    Jimmy
    -0.06
    rique
    -0.06
    POSITIVE LOGITS
    阍
    0.07
     개념
    0.07
    赞赏
    0.07
     Turing
    0.07
    首饰
    0.07
    ileges
    0.06
    ব
    0.06
    ?”
    0.06
    ?)
    0.06
    艇
    0.06
    Act Density 0.128%

    No Known Activations