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

    Neuronpedia

    INDEX
    Explanations

    Code/Markup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.08
     hott
    -0.08
     by
    -0.08
     поч
    -0.08
     rotary
    -0.07
    Workbook
    -0.07
    etimes
    -0.07
    tplib
    -0.07
    ffi
    -0.07
     of
    -0.07
    POSITIVE LOGITS
    十三条
    0.07
    še
    0.07
    form
    0.07
    0.07
    §
    0.07
    𝐒
    0.07
     scroll
    0.07
    _membership
    0.07
    ﺿ
    0.07
    进出
    0.07
    Act Density 0.005%

    No Known Activations