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

    Neuronpedia

    INDEX
    Explanations

    writing sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BP
    -0.07
     lens
    -0.06
     lenses
    -0.06
     Gregory
    -0.06
    -all
    -0.06
    (pb
    -0.06
     superst
    -0.06
    eral
    -0.06
    .assertEqual
    -0.06
    眼睛
    -0.06
    POSITIVE LOGITS
    papers
    0.07
     �
    0.06
    lime
    0.06
    usu
    0.06
    ุลาคม
    0.06
     адміністратив
    0.06
     dealloc
    0.06
     barely
    0.06
    イズ
    0.06
    lotte
    0.06
    Act Density 0.021%

    No Known Activations