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

    Neuronpedia

    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wel
    -0.07
     arttır
    -0.07
    mür
    -0.06
    вий
    -0.06
    Sparse
    -0.06
    StdString
    -0.06
     grandi
    -0.06
    佐
    -0.06
    CBS
    -0.06
     landscapes
    -0.06
    POSITIVE LOGITS
    -touch
    0.09
     Thing
    0.09
     thing
    0.08
    chure
    0.07
    Touch
    0.07
     �
    0.07
     shines
    0.07
    ترنت
    0.06
    ilinx
    0.06
    -handle
    0.06
    Act Density 0.011%

    No Known Activations