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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    functional
    -0.07
    'L
    -0.06
    526
    -0.06
    ùa
    -0.06
     Rosa
    -0.06
     PCs
    -0.06
    AINS
    -0.06
    써
    -0.06
    )L
    -0.06
     lodge
    -0.06
    POSITIVE LOGITS
     whims
    0.06
     کری
    0.06
     Coronavirus
    0.06
     zru
    0.06
     Student
    0.06
     Друг
    0.06
     금액
    0.06
     زیادی
    0.06
    має
    0.06
    нию
    0.06
    Act Density 0.585%

    No Known Activations