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

    Neuronpedia

    INDEX
    Explanations

    previous fixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Գ
    1.26
    žno
    1.15
     Nederland
    1.09
    anno
    1.07
    ター
    0.98
     মো
    0.98
     суме
    0.97
    Política
    0.96
     België
    0.95
    )^(
    0.92
    POSITIVE LOGITS
     hadrons
    1.40
    𝖐
    1.38
     nicer
    1.33
    不管
    1.25
     uncorrelated
    1.25
     جذاب
    1.24
    œurs
    1.22
     homely
    1.21
     Ronan
    1.20
     microturbulence
    1.19
    Act Density 0.000%

    No Known Activations