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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dex
    -0.07
    Dup
    -0.06
    RSS
    -0.06
     正
    -0.06
     pants
    -0.06
    照
    -0.06
     измер
    -0.06
    .sex
    -0.06
    ्टर
    -0.05
    έρ
    -0.05
    POSITIVE LOGITS
     presidente
    0.07
    และส
    0.07
    _lr
    0.06
    ryptography
    0.06
    yš
    0.06
     فاصله
    0.06
    และม
    0.06
    ARC
    0.06
    �
    0.06
     deactivated
    0.06
    Act Density 0.018%

    No Known Activations