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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phạm
    -0.07
     alo
    -0.07
     hơn
    -0.07
    いる
    -0.07
     Significant
    -0.07
    numpy
    -0.06
     довольно
    -0.06
     crispy
    -0.06
    DataReader
    -0.06
    fair
    -0.06
    POSITIVE LOGITS
     Hubbard
    0.07
    تس
    0.06
     cas
    0.06
    quarters
    0.06
    .Try
    0.06
    راد
    0.06
     vent
    0.06
    �
    0.06
     agony
    0.06
     narr
    0.06
    Act Density 0.007%

    No Known Activations