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

    Neuronpedia

    INDEX
    Explanations

    loses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .LoggerFactory
    -0.07
    ในการ
    -0.07
     Bh
    -0.06
     chops
    -0.06
    bage
    -0.06
     MLM
    -0.06
     Backpack
    -0.06
    .angle
    -0.06
    ，而
    -0.06
    px
    -0.06
    POSITIVE LOGITS
    _)
    0.06
    /pol
    0.06
    Nous
    0.06
    abytes
    0.06
    ливих
    0.06
     Amsterdam
    0.06
    ।
    0.06
     Fun
    0.06
     çift
    0.06
    WASHINGTON
    0.06
    Act Density 0.054%

    No Known Activations