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

    Neuronpedia

    INDEX
    Explanations

    research paper snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <>
    -0.07
    -Semitic
    -0.07
     Qualcomm
    -0.07
    Psi
    -0.07
    상을
    -0.07
     февраля
    -0.07
    ommen
    -0.07
    물
    -0.07
    intersection
    -0.07
     khí
    -0.07
    POSITIVE LOGITS
    torrent
    0.07
    㙍
    0.06
    VEL
    0.06
    IND
    0.06
    收紧
    0.06
    的相关
    0.06
    积极作用
    0.06
    _SETTINGS
    0.06
     firsthand
    0.06
    _stream
    0.06
    Act Density 0.118%

    No Known Activations