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

    Neuronpedia

    INDEX
    Explanations

    Algorithm efficiency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mail
    -0.07
     onNext
    -0.06
    -0.06
     Owner
    -0.06
     Baldwin
    -0.06
    .firebaseapp
    -0.06
     شهرهای
    -0.06
    _aux
    -0.06
     Erect
    -0.06
     Checks
    -0.06
    POSITIVE LOGITS
     kk
    0.07
    reflect
    0.07
     strate
    0.06
     меньше
    0.06
    ocumented
    0.06
    Figure
    0.06
     останні
    0.06
    COMM
    0.06
     Králové
    0.06
    phan
    0.06
    Act Density 0.008%

    No Known Activations