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

    Neuronpedia

    INDEX
    Explanations

    focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Regul
    -0.09
    rem
    -0.08
     remov
    -0.08
    acles
    -0.07
    Washington
    -0.07
     herinner
    -0.07
    Tau
    -0.07
    Recovery
    -0.07
     thoughtfully
    -0.07
    rega
    -0.07
    POSITIVE LOGITS
     हासिल
    0.09
     ''↵↵
    0.09
     ՝
    0.08
     mener
    0.08
     աշխատ
    0.08
     սկս
    0.08
     повыш
    0.08
     սիրում
    0.08
    ՝
    0.08
     visando
    0.08
    Act Density 0.002%

    No Known Activations