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

    Neuronpedia

    INDEX
    Explanations

    instructions and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dieser
    0.42
    Also
    0.40
    also
    0.38
     일
    0.37
    Lance
    0.37
     ايضا
    0.37
    льных
    0.36
    ді
    0.36
    Съ
    0.36
    ruch
    0.36
    POSITIVE LOGITS
     trends
    0.44
    しやすい
    0.40
     방법에
    0.40
     biotech
    0.39
     Par
    0.39
     Cir
    0.39
     abnormalities
    0.39
     SupCt
    0.38
     GeV
    0.38
     Biotech
    0.38
    Act Density 0.074%

    No Known Activations