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

    Neuronpedia

    INDEX
    Explanations

    goal is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бре
    0.46
     έξ
    0.39
     सोया
    0.39
     gotovo
    0.38
     anhydrous
    0.38
    Lavender
    0.38
     לב
    0.38
    ロイ
    0.38
     đậm
    0.37
     }},
    0.37
    POSITIVE LOGITS
    ટી
    0.44
     ምስ
    0.40
     operativa
    0.38
    ontal
    0.38
    istrano
    0.38
     Agust
    0.37
    supers
    0.37
     Hackett
    0.37
    بحث
    0.37
     aggreg
    0.36
    Act Density 0.000%

    No Known Activations