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

    Neuronpedia

    INDEX
    Explanations

    sec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ჩ
    -0.08
    ♝
    -0.07
    Ав
    -0.07
    .cs
    -0.07
     Cv
    -0.07
     pav
    -0.07
     Supply
    -0.07
     böl
    -0.07
    .deb
    -0.07
    David
    -0.07
    POSITIVE LOGITS
    aciente
    0.07
    pectrum
    0.07
    某种
    0.07
    ffective
    0.06
    롓
    0.06
    东方
    0.06
    海上
    0.06
    不过是
    0.06
    稍微
    0.06
    碴
    0.06
    Act Density 0.000%

    No Known Activations