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

    Neuronpedia

    INDEX
    Explanations

    deservingness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WITH
    0.50
     Giant
    0.50
    可能
    0.49
     podrás
    0.48
    k
    0.48
     E
    0.47
     تأثير
    0.47
     LAT
    0.47
     U
    0.46
     Tuesdays
    0.46
    POSITIVE LOGITS
     deserve
    0.87
     deserves
    0.86
     deserved
    0.85
     deserving
    0.74
     заслу
    0.70
     merece
    0.63
     mérite
    0.61
     layak
    0.57
     worthy
    0.56
     rightfully
    0.52
    Act Density 0.040%

    No Known Activations