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
    serious
    -0.07
     Fus
    -0.07
     Cannes
    -0.07
    绚丽
    -0.07
     falling
    -0.06
     libros
    -0.06
    Anthony
    -0.06
    "x
    -0.06
     Trem
    -0.06
     הרב
    -0.06
    POSITIVE LOGITS
    .getTime
    0.08
    ,%
    0.07
    改制
    0.07
    حال
    0.07
    佃
    0.07
     DOC
    0.06
     Money
    0.06
    以前
    0.06
    host
    0.06
    CellStyle
    0.06
    Act Density 0.020%

    No Known Activations