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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çab
    -0.07
    -Type
    -0.07
    ा)
    -0.07
    داشت
    -0.07
    博物
    -0.07
    <Message
    -0.07
     Adjustable
    -0.06
    �
    -0.06
    (sem
    -0.06
     Fetch
    -0.06
    POSITIVE LOGITS
    chn
    0.06
    เทศ
    0.06
     ділян
    0.06
    ืน
    0.05
     øns
    0.05
    chk
    0.05
     규
    0.05
    aft
    0.05
    거
    0.05
     geometric
    0.05
    Act Density 0.124%

    No Known Activations