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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اعي
    -0.07
    baru
    -0.07
    ланд
    -0.07
     mais
    -0.07
    -social
    -0.07
    WiFi
    -0.07
    ///↵↵
    -0.06
    Unix
    -0.06
    .Parcelable
    -0.06
    REATED
    -0.06
    POSITIVE LOGITS
     )
↵
    0.07
     )
    0.07
     ){↵
    0.06
     مي
    0.06
     ]
    0.06
    ?><
    0.06
    َة
    0.06
     �
    0.06
     قي
    0.06
         
    0.06
    Act Density 0.020%

    No Known Activations