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

    Neuronpedia

    INDEX
    Explanations

    choose or select

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."—
    0.44
     CONDITION
    0.43
    "/"
    0.40
    "?
    0.40
    ]."
    0.40
    ментів
    0.40
     ONLY
    0.39
    "./
    0.38
    ."-
    0.38
     थांब
    0.38
    POSITIVE LOGITS
     choosing
    0.61
     choose
    0.55
     chooses
    0.55
    選擇
    0.51
    选择
    0.49
     wyb
    0.48
     elegir
    0.48
     wählen
    0.48
     arranges
    0.48
     pemilihan
    0.47
    Act Density 0.001%

    No Known Activations