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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пот
    -0.07
    .LinearLayout
    -0.07
    ičky
    -0.06
    (rawValue
    -0.06
    Dia
    -0.06
     cabinets
    -0.06
    ________________
    -0.06
    BX
    -0.06
    ave
    -0.06
    ув
    -0.06
    POSITIVE LOGITS
     earns
    0.07
     tải
    0.07
    .tolist
    0.06
     stool
    0.06
     earned
    0.06
    _seqs
    0.06
     milestone
    0.06
    758
    0.06
     jou
    0.06
     tóc
    0.06
    Act Density 0.003%

    No Known Activations