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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     urg
    -0.07
    -‐
    -0.06
     bottoms
    -0.06
     nf
    -0.06
     tw
    -0.06
     cha
    -0.06
    _BUF
    -0.06
    _ch
    -0.06
     bile
    -0.06
    POSITIVE LOGITS
    ्ञ
    0.06
     Gro
    0.06
     exporter
    0.06
    _fast
    0.06
    يكي
    0.06
     smugg
    0.06
     interoper
    0.06
    日本
    0.06
     miêu
    0.06
     Modifications
    0.06
    Act Density 0.008%

    No Known Activations