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

    Neuronpedia

    INDEX
    Explanations

    divergence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     third
    0.49
    iz
    0.48
     today
    0.47
     minute
    0.45
     sangat
    0.45
     democratic
    0.45
     kabar
    0.44
     Kreis
    0.44
     réunis
    0.44
     prime
    0.43
    POSITIVE LOGITS
    Ρ
    0.46
    推理
    0.46
    。。。。
    0.46
    祛
    0.44
     ję
    0.44
    プス
    0.43
    ēn
    0.43
     სტ
    0.42
    初步
    0.42
    𝔾
    0.42
    Act Density 0.002%

    No Known Activations