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

    Neuronpedia

    INDEX
    Explanations

    narratives/storytelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    block
    -0.07
    ống
    -0.07
    อลลาร
    -0.06
     commuters
    -0.06
     ruler
    -0.06
    -aligned
    -0.06
    step
    -0.06
     RD
    -0.06
    variants
    -0.06
    HEEL
    -0.06
    POSITIVE LOGITS
     ам
    0.07
    ่ได
    0.07
    .EX
    0.06
    .addComponent
    0.06
    ább
    0.06
    анні
    0.06
    (i
    0.06
    推薦
    0.06
     omission
    0.06
     đị
    0.06
    Act Density 0.117%

    No Known Activations