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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poměrně
    -0.07
    ROLLER
    -0.07
     servicios
    -0.06
     racer
    -0.06
    くら
    -0.06
     sayesinde
    -0.06
     regulator
    -0.06
     grid
    -0.06
    002
    -0.06
    _mD
    -0.06
    POSITIVE LOGITS
    Chicken
    0.06
    沒有
    0.06
     Wine
    0.06
     Messaging
    0.06
    bew
    0.06
     Chicken
    0.06
    _weights
    0.06
     외국
    0.06
    urname
    0.06
    _UTF
    0.06
    Act Density 0.030%

    No Known Activations