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

    Neuronpedia

    INDEX
    Explanations

    Codes and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肱
    -0.07
     KDE
    -0.07
    elow
    -0.06
    重构
    -0.06
    됄
    -0.06
    .crm
    -0.06
     ade
    -0.06
     לכל
    -0.06
    쫌
    -0.06
    /Set
    -0.06
    POSITIVE LOGITS
    <Comment
    0.07
    	flags
    0.07
    _count
    0.07
    ptype
    0.07
     opposition
    0.07
    hower
    0.07
    inity
    0.07
    两条
    0.07
    �
    0.07
     FIN
    0.06
    Act Density 0.016%

    No Known Activations