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

    Neuronpedia

    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ئت
    -0.08
    根本就不
    -0.07
    urent
    -0.07
     millennium
    -0.07
     ก
    -0.07
    刻苦
    -0.07
     Lexus
    -0.07
    Witness
    -0.06
    ∆
    -0.06
    话语
    -0.06
    POSITIVE LOGITS
    Postal
    0.07
     theatrical
    0.07
    placing
    0.07
    _rows
    0.07
    私は
    0.07
     obrig
    0.07
     har
    0.06
     installations
    0.06
    .padding
    0.06
    \">
    0.06
    Act Density 0.004%

    No Known Activations