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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    看待
    -0.07
     Tran
    -0.07
    ilitating
    -0.07
     surge
    -0.06
    /stat
    -0.06
     triangular
    -0.06
    Fl
    -0.06
    quiries
    -0.06
    맆
    -0.06
    行李
    -0.06
    POSITIVE LOGITS
    ✯
    0.08
    crawler
    0.07
    .processor
    0.07
    _footer
    0.07
    مارك
    0.07
     Install
    0.07
    יסוד
    0.07
    散户
    0.06
    liter
    0.06
    fullscreen
    0.06
    Act Density 0.017%

    No Known Activations