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

    Neuronpedia

    INDEX
    Explanations

    single, one, or few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ukat
    0.43
     Verlet
    0.43
     частично
    0.40
    omethyl
    0.39
     baisse
    0.38
     Dezember
    0.37
     भाज
    0.37
     নীর
    0.37
     Certain
    0.36
     გარ
    0.36
    POSITIVE LOGITS
     single
    1.81
    single
    1.71
    单一
    1.69
    Single
    1.66
     SINGLE
    1.60
     Single
    1.54
    只有一个
    1.48
    SINGLE
    1.47
    单
    1.44
    單
    1.34
    Act Density 0.740%

    No Known Activations