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

    Neuronpedia

    INDEX
    Explanations

    saving csv without index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    руса
    0.40
     dide
    0.40
     PTE
    0.39
    ўным
    0.39
     DME
    0.39
    uada
    0.38
    스코
    0.38
    spra
    0.38
     ď
    0.37
    separation
    0.37
    POSITIVE LOGITS
     novia
    0.43
     बाहर
    0.42
     Séance
    0.39
    gfx
    0.38
     Manch
    0.38
     çizg
    0.37
    Ke
    0.35
     без
    0.35
    Chez
    0.35
    গ্রাফ
    0.34
    Act Density 0.000%

    No Known Activations