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

    Neuronpedia

    INDEX
    Explanations

    more detail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мет
    -0.06
    .remove
    -0.06
     مك
    -0.06
     Ler
    -0.06
    Packages
    -0.06
    нику
    -0.06
    าคา
    -0.06
    <u
    -0.06
    在线观看
    -0.06
    ارات
    -0.06
    POSITIVE LOGITS
    phy
    0.08
    mond
    0.07
    annes
    0.07
     Parker
    0.07
    lete
    0.07
     Gwen
    0.07
     BILL
    0.07
    ighb
    0.07
    NTAX
    0.06
    ctor
    0.06
    Act Density 0.079%

    No Known Activations