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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =<?=
    -0.07
     yaptığ
    -0.07
    ضل
    -0.07
    -bs
    -0.06
     serde
    -0.06
     aber
    -0.06
     utiliza
    -0.06
     základě
    -0.06
    ria
    -0.06
     ARP
    -0.06
    POSITIVE LOGITS
    оли
    0.07
     sympathetic
    0.07
     whoever
    0.07
    (require
    0.06
     dismissing
    0.06
    umsuz
    0.06
    ори
    0.06
    _performance
    0.06
     Bai
    0.06
     adrenal
    0.06
    Act Density 0.000%

    No Known Activations