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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HEIGHT
    -0.07
     fait
    -0.06
    avatel
    -0.06
     місті
    -0.06
     letzten
    -0.06
     swell
    -0.06
     선
    -0.06
    akespeare
    -0.06
    hal
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     workings
    0.07
     prepares
    0.07
    0.06
    .commit
    0.06
    erged
    0.06
     Uran
    0.06
    ****************************************
    0.06
    _logged
    0.06
     DS
    0.06
     advertised
    0.06
    Act Density 0.007%

    No Known Activations