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

    Neuronpedia

    INDEX
    Explanations

    other classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.62
    5
    0.52
    0.50
    <0xEE>
    0.49
    -
    0.49
    0
    0.48
    <0x0D>
    0.45
    6
    0.45
     visibly
    0.44
    =
    0.44
    POSITIVE LOGITS
    绁
    0.60
    쮿
    0.58
    敺
    0.54
    dır
    0.54
    میم
    0.53
    getNumber
    0.52
    လိုအပ်
    0.52
     związane
    0.51
    㤈
    0.51
     परवरिश
    0.50
    Act Density 0.000%

    No Known Activations