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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    isans
    -0.07
    erap
    -0.07
    ethical
    -0.07
    bal
    -0.06
     letter
    -0.06
    ISA
    -0.06
    ิบ
    -0.06
    >Note
    -0.06
    Beer
    -0.06
    POSITIVE LOGITS
    umbed
    0.07
     с
    0.07
     Sed
    0.07
     je
    0.07
    /LICENSE
    0.06
     plunder
    0.06
    .body
    0.06
    (Bitmap
    0.06
     docker
    0.06
    =b
    0.06
    Act Density 0.002%

    No Known Activations