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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    搌
    -0.07
    碌
    -0.07
     Oliv
    -0.07
    Locked
    -0.07
    .tell
    -0.07
    📡
    -0.07
    elementType
    -0.07
     sucked
    -0.07
     Tantra
    -0.07
    潾
    -0.07
    POSITIVE LOGITS
     organizing
    0.08
     Verb
    0.07
    <>↵
    0.07
    College
    0.07
    西湖
    0.06
    ４
    0.06
    发动机
    0.06
     Presbyterian
    0.06
    stag
    0.06
    信
    0.06
    Act Density 0.003%

    No Known Activations