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

    Neuronpedia

    INDEX
    Explanations

    Correctness and validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wyświetl
    -0.07
     flagged
    -0.07
    /platform
    -0.06
     throwable
    -0.06
    准
    -0.06
    อำน
    -0.06
     Canadian
    -0.06
     guild
    -0.06
    常态
    -0.06
    cr
    -0.06
    POSITIVE LOGITS
     .=
    0.08
    ｃ
    0.07
     хозяйств
    0.07
    خمس
    0.07
    /mail
    0.07
    /time
    0.07
    隐蔽
    0.07
    ｈ
    0.07
    เผย
    0.07
    うま
    0.07
    Act Density 0.124%

    No Known Activations