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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Advertising
    -0.07
     Olymp
    -0.07
     waterfront
    -0.07
     第二
    -0.07
     státu
    -0.07
     společ
    -0.07
    ):
    -0.07
     TD
    -0.07
    ')
    -0.07
     kisses
    -0.06
    POSITIVE LOGITS
    lerine
    0.06
    anggan
    0.06
    noloj
    0.06
    irim
    0.06
    الة
    0.06
    合わせ
    0.06
    รายการ
    0.05
     Northeast
    0.05
    徒歩
    0.05
     turbine
    0.05
    Act Density 0.001%

    No Known Activations