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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ером
    -0.07
     muj
    -0.07
     Ug
    -0.07
    Today
    -0.06
    editor
    -0.06
    if
    -0.06
    -article
    -0.06
    /env
    -0.06
    onn
    -0.06
     Columns
    -0.06
    POSITIVE LOGITS
     PROFITS
    0.07
    .ST
    0.07
    .habbo
    0.07
    _INV
    0.07
    είτε
    0.07
     katıl
    0.06
     excluding
    0.06
    _GT
    0.06
    就在
    0.06
    .PR
    0.06
    Act Density 0.018%

    No Known Activations