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

    Neuronpedia

    INDEX
    Explanations

    distance and location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.57
    ון
    0.57
    اعری
    0.54
    स्टिक
    0.53
    壹章
    0.50
    ]));
    0.49
    制造
    0.47
    执
    0.47
    利的
    0.47
    实现了
    0.46
    POSITIVE LOGITS
     dauer
    0.46
    ร
    0.44
    lings
    0.42
     F
    0.41
     E
    0.41
     polymer
    0.41
     PL
    0.40
     Pluto
    0.40
    iggle
    0.40
     Plut
    0.40
    Act Density 0.000%

    No Known Activations