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

    Neuronpedia

    INDEX
    Explanations

    setting plot elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ವ
    0.41
     مِنْ
    0.41
    ്രീ
    0.41
    मेह
    0.40
    AssetDiscovery
    0.40
     Newly
    0.39
     criada
    0.39
     шуда
    0.39
     کھول
    0.38
    ቼ
    0.38
    POSITIVE LOGITS
     face
    0.58
     xlabel
    0.48
    face
    0.48
    ylabel
    0.47
     лице
    0.47
    xlabel
    0.46
     ylabel
    0.46
     aspect
    0.45
    xt
    0.44
     Face
    0.43
    Act Density 0.002%

    No Known Activations