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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _different
    -0.07
     doubly
    -0.06
    Always
    -0.06
     lowers
    -0.06
    واء
    -0.06
     happily
    -0.06
    ogui
    -0.06
     зов
    -0.06
    always
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ��索
    0.07
     yüzden
    0.07
    //*[@
    0.07
     Louisville
    0.06
    -*-
    0.06
    xc
    0.06
     algunos
    0.06
     Brook
    0.06
     İstanbul
    0.06
    537
    0.06
    Act Density 0.000%

    No Known Activations