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

    Neuronpedia

    INDEX
    Explanations

    file paths and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nœ
    0.45
     obie
    0.44
     generar
    0.44
     ocorreu
    0.44
     existe
    0.43
     ontology
    0.43
     aparición
    0.43
     especificar
    0.42
     sende
    0.42
     senden
    0.42
    POSITIVE LOGITS
    jpg
    0.63
    img
    0.57
     jpg
    0.56
    thumbnails
    0.56
    IMG
    0.55
    _'.$
    0.55
    最终
    0.53
    images
    0.52
    图像
    0.51
     JPG
    0.50
    Act Density 0.139%

    No Known Activations