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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pract
    -0.08
     conjunto
    -0.08
     célib
    -0.07
    Container
    -0.07
     kond
    -0.07
     king
    -0.07
     Buckingham
    -0.07
     Prince
    -0.07
     clan
    -0.07
    'use
    -0.07
    POSITIVE LOGITS
    Error
    0.14
     error
    0.13
     Error
    0.12
     errors
    0.11
    error
    0.10
    Err
    0.09
    (error
    0.09
     ERROR
    0.09
    _ERRORS
    0.09
    Errors
    0.08
    Act Density 0.050%

    No Known Activations