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

    Neuronpedia

    INDEX
    Explanations

    cover letter for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ি
    1.89
    یه
    1.88
    Tuy
    1.73
    ية
    1.69
     acabou
    1.67
     tahap
    1.66
     Veja
    1.65
     जगहों
    1.63
    ி
    1.63
     necessari
    1.60
    POSITIVE LOGITS
    pillar
    1.63
    у
    1.61
    atura
    1.53
     Invasion
    1.51
    ties
    1.51
    ﺓ
    1.50
    ned
    1.48
    scapes
    1.45
    nullptr
    1.43
    Seal
    1.40
    Act Density 0.014%

    No Known Activations