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

    Neuronpedia

    INDEX
    Explanations

    code returning values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gosudarstvennyj
    0.45
    SRPC
    0.43
    BtnFill
    0.41
    VSLU
    0.41
    BlockUsed
    0.40
    Blooming
    0.40
    őbb
    0.39
    Références
    0.39
    Revel
    0.39
    Cul
    0.39
    POSITIVE LOGITS
     these
    0.70
     this
    0.70
     the
    0.60
     it
    0.58
    this
    0.56
     that
    0.52
    .
    0.49
     aceste
    0.49
     tersebut
    0.49
    these
    0.48
    Act Density 0.387%

    No Known Activations