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

    Neuronpedia

    INDEX
    Explanations

    Interviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ningen
    -0.08
     Revenue
    -0.07
    (vis
    -0.07
    @test
    -0.07
    صحة
    -0.07
    ドラマ
    -0.07
    -invalid
    -0.07
     poorer
    -0.07
    ivement
    -0.07
    (@"
    -0.07
    POSITIVE LOGITS
     libs
    0.07
     �
    0.07
    (co
    0.07
    arbonate
    0.07
    ��
    0.07
    Ẫ
    0.06
     mim
    0.06
    �
    0.06
    STE
    0.06
     abound
    0.06
    Act Density 0.016%

    No Known Activations