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

    Neuronpedia

    INDEX
    Explanations

    sorting algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    отя
    0.46
     해야
    0.46
    ૭
    0.45
    𝙮
    0.45
     dobbiamo
    0.44
    мії
    0.44
    ༥
    0.44
     impatience
    0.43
    oplayer
    0.42
    ಡ್
    0.41
    POSITIVE LOGITS
     This
    0.72
     Provides
    0.69
    This
    0.67
     Describes
    0.66
     describes
    0.65
     Creates
    0.64
     Represents
    0.63
     Tämä
    0.60
    Describes
    0.58
     Adds
    0.58
    Act Density 0.007%

    No Known Activations