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

    Neuronpedia

    INDEX
    Explanations

    organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    血
    -0.07
    ственным
    -0.06
    Watch
    -0.06
     Doğum
    -0.06
    �
    -0.06
     dünya
    -0.06
    Blood
    -0.06
     rumpe
    -0.06
    ような
    -0.06
    Fail
    -0.06
    POSITIVE LOGITS
     unto
    0.07
     @$
    0.06
    �
    0.06
    .iteritems
    0.06
     Sydney
    0.06
     터
    0.06
    GU
    0.06
    提供
    0.06
    ницт
    0.06
    íst
    0.05
    Act Density 0.075%

    No Known Activations