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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plex
    -0.07
    御
    -0.06
     superficial
    -0.06
    .progressBar
    -0.06
    .Frame
    -0.06
     suddenly
    -0.06
    ellschaft
    -0.06
    ูง
    -0.06
    cyan
    -0.06
     августа
    -0.06
    POSITIVE LOGITS
    ayi
    0.08
    /interface
    0.07
    _seek
    0.07
    ROTO
    0.06
    ];↵
    0.06
    framework
    0.06
     tầng
    0.06
    ’é
    0.06
     defaults
    0.06
    enton
    0.06
    Act Density 0.000%

    No Known Activations