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

    Neuronpedia

    INDEX
    Explanations

    places for young

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genre
    0.72
     lovable
    0.71
     Eyre
    0.70
     corredor
    0.70
     tööt
    0.69
    亏
    0.69
    বিজ্ঞান
    0.69
    鲤
    0.68
     diesel
    0.68
     mecánica
    0.67
    POSITIVE LOGITS
     nests
    1.81
     nest
    1.74
     Nest
    1.43
    Nest
    1.39
     nesting
    1.27
     tents
    1.20
    巢
    1.12
     tent
    1.10
    NEST
    1.09
     huts
    1.07
    Act Density 0.163%

    No Known Activations