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

    Neuronpedia

    INDEX
    Explanations

    cryptography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    误
    -0.07
    िम
    -0.07
    520
    -0.07
     示
    -0.07
    知道
    -0.07
    楚
    -0.06
    母亲
    -0.06
    hard
    -0.06
     zoekt
    -0.06
    üns
    -0.06
    POSITIVE LOGITS
    ‐‐
    0.07
    .RELATED
    0.07
    στημα
    0.06
    (display
    0.06
    _Top
    0.06
    _Trans
    0.06
    @author
    0.06
     Entrepreneur
    0.06
     країн
    0.06
    .Failure
    0.06
    Act Density 0.118%

    No Known Activations