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

    Neuronpedia

    INDEX
    Explanations

    device

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PARSE
    -0.07
    ilty
    -0.07
    NG
    -0.07
     Ike
    -0.07
    ीट
    -0.07
    Broken
    -0.07
    _bill
    -0.07
    Ice
    -0.06
    -oriented
    -0.06
     ICE
    -0.06
    POSITIVE LOGITS
    所有
    0.07
    .netty
    0.06
    _Device
    0.06
    ecut
    0.06
    (callback
    0.06
     �
    0.06
     ἀ
    0.06
     Kentucky
    0.06
     τη
    0.06
     지정
    0.06
    Act Density 0.007%

    No Known Activations