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

    Neuronpedia

    INDEX
    Explanations

    one-size-fits-all doesn't work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     striker
    -0.07
     overl
    -0.07
     xrange
    -0.07
     Ten
    -0.06
    ��
    -0.06
     thang
    -0.06
     Muk
    -0.06
     {},
    -0.06
     öğrenc
    -0.06
     Liquid
    -0.06
    POSITIVE LOGITS
    #endregion
    0.06
    pově
    0.06
    bie
    0.06
    +c
    0.06
    jmu
    0.06
     �
    0.06
     PRODUCT
    0.06
    аков
    0.06
    pdev
    0.06
     odpově
    0.06
    Act Density 0.003%

    No Known Activations