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

    Neuronpedia

    INDEX
    Explanations

    if... then.

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tinha
    0.54
     maîtrise
    0.48
     gris
    0.44
     नव्ह
    0.43
     nhất
    0.43
     huit
    0.43
     드릴
    0.43
     tenía
    0.43
    înes
    0.43
    leme
    0.43
    POSITIVE LOGITS
     Developments
    0.51
    Du
    0.51
    U
    0.50
    辐
    0.47
     Bake
    0.46
    Aq
    0.46
    Draft
    0.45
    Approved
    0.44
     Regression
    0.44
    Economics
    0.44
    Act Density 0.013%

    No Known Activations