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
     teenager
    -0.07
     curr
    -0.07
    SEND
    -0.07
     mourn
    -0.07
     breathe
    -0.07
     curiosity
    -0.07
     ké
    -0.07
    _reduce
    -0.07
    尿
    -0.07
    端午
    -0.07
    POSITIVE LOGITS
    ꧊
    0.09
    ﻍ
    0.08
     экон
    0.07
    ḅ
    0.07
    蠊
    0.07
    (coll
    0.07
    .YesNo
    0.07
     ......
    0.07
    .controls
    0.06
    고
    0.06
    Act Density 0.002%

    No Known Activations