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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Serena
    -0.07
     bảng
    -0.07
     counts
    -0.07
    SmartyHeaderCode
    -0.07
    .`,↵
    -0.07
     psychologically
    -0.07
    总会
    -0.07
     agrees
    -0.06
     pledges
    -0.06
    (Grid
    -0.06
    POSITIVE LOGITS
     רו
    0.07
    _empty
    0.07
    bonus
    0.06
    unch
    0.06
    incer
    0.06
    מח
    0.06
    int
    0.06
     Tiên
    0.06
    inus
    0.06
    unit
    0.06
    Act Density 0.001%

    No Known Activations