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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    �
    -0.07
    -Se
    -0.07
    דרוש
    -0.07
    詹
    -0.07
    -layout
    -0.07
    _APPLICATION
    -0.07
    옇
    -0.07
    担心
    -0.07
    <strong
    -0.07
    🌻
    -0.07
    POSITIVE LOGITS
     Зна
    0.07
    ()}>↵
    0.07
    _cookie
    0.07
    PLAY
    0.07
    ">↵
    0.07
     kilometers
    0.07
    壤
    0.07
    歲
    0.06
    efault
    0.06
    尽力
    0.06
    Act Density 0.000%

    No Known Activations