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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aldo
    -0.08
    _FA
    -0.07
     spect
    -0.07
    .Popup
    -0.06
     IPT
    -0.06
     deficient
    -0.06
     širo
    -0.06
     amis
    -0.06
     watchers
    -0.06
     wartime
    -0.06
    POSITIVE LOGITS
    Rate
    0.08
    ################################################################
    0.07
     admission
    0.07
     tạo
    0.07
    Ä
    0.06
    =<?=
    0.06
    Ｌ
    0.06
    ======↵
    0.06
    색
    0.06
    造
    0.06
    Act Density 0.000%

    No Known Activations