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

    Neuronpedia

    INDEX
    Explanations

    perfect shirts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सरसों
    0.43
    挀
    0.42
    劇場
    0.38
     নিজে
    0.38
    眼
    0.37
     Recogn
    0.37
     recognize
    0.37
     optic
    0.36
     भरने
    0.36
     ausgesch
    0.36
    POSITIVE LOGITS
    perfect
    0.46
    Perfect
    0.41
     Shirt
    0.40
     redness
    0.40
    glomer
    0.40
     PERFECT
    0.40
    coh
    0.39
    redu
    0.39
    coherent
    0.38
     Red
    0.38
    Act Density 0.001%

    No Known Activations