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

    Neuronpedia

    INDEX
    Explanations

    French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     executed
    -0.07
     wś
    -0.07
    合法权益
    -0.07
     Gay
    -0.06
     printk
    -0.06
    rod
    -0.06
    ถ
    -0.06
    くなって
    -0.06
    Setup
    -0.06
     Cass
    -0.06
    POSITIVE LOGITS
     Tos
    0.08
    瞪
    0.08
    _sc
    0.07
    (fields
    0.07
    .foreach
    0.07
    uls
    0.07
     dfs
    0.07
    꺅
    0.07
    (face
    0.07
    _under
    0.07
    Act Density 0.005%

    No Known Activations