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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    칠
    -0.07
     रखन
    -0.07
    　l
    -0.06
     němu
    -0.06
     uměl
    -0.06
    _inline
    -0.06
    OMBRE
    -0.06
    phet
    -0.06
     вихов
    -0.06
     reviewer
    -0.06
    POSITIVE LOGITS
     casualty
    0.06
     Visa
    0.06
    izm
    0.06
     tank
    0.06
    izzie
    0.06
     Lung
    0.06
     diving
    0.06
    ….↵↵
    0.06
     Lang
    0.06
     disgu
    0.06
    Act Density 0.015%

    No Known Activations