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

    Neuronpedia

    INDEX
    Explanations

    advice and offering solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пане
    0.49
     单位
    0.48
     Mussolini
    0.46
     obligado
    0.46
     収納
    0.46
     festiv
    0.45
    🥶
    0.45
    tabPage
    0.45
     unidad
    0.44
     bane
    0.44
    POSITIVE LOGITS
    ốt
    0.44
    ermark
    0.41
    는
    0.40
    ኽ
    0.40
    김
    0.39
    Major
    0.38
    简介
    0.38
    提高
    0.38
    ีย
    0.38
    江西
    0.37
    Act Density 0.000%

    No Known Activations