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

    Neuronpedia

    INDEX
    Explanations

    Executions and death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     맡
    -0.07
     الأم
    -0.07
    Administr
    -0.06
     curious
    -0.06
    	else
    -0.06
     후기
    -0.06
    EXPECTED
    -0.06
     entrenched
    -0.06
     статьи
    -0.06
    True
    -0.06
    POSITIVE LOGITS
     νεφοκάλυψης
    0.07
    abol
    0.07
    Byte
    0.06
     BusinessException
    0.06
    LEGRO
    0.06
    endencies
    0.06
    ًا
    0.06
     Chapter
    0.06
     {}",
    0.06
    .`|`↵
    0.06
    Act Density 0.021%

    No Known Activations