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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    爽
    -0.07
     За
    -0.07
     سفید
    -0.06
    Jamie
    -0.06
    Detection
    -0.06
    -С
    -0.06
    ，要
    -0.06
    堡
    -0.06
     Semiconductor
    -0.06
    _INVALID
    -0.06
    POSITIVE LOGITS
     obviously
    0.07
     Rhodes
    0.06
    -game
    0.06
    절
    0.06
     display
    0.06
     pstmt
    0.06
    edback
    0.06
    came
    0.06
    published
    0.06
    petition
    0.06
    Act Density 0.002%

    No Known Activations