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

    Neuronpedia

    INDEX
    Explanations

    individual cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lug
    0.49
    Wyn
    0.48
    al
    0.46
    Jer
    0.46
    Butter
    0.45
    Sil
    0.45
    an
    0.44
    Gmail
    0.44
    Work
    0.43
     Lug
    0.43
    POSITIVE LOGITS
     vérit
    0.50
    utors
    0.49
     médicas
    0.48
     jurisdict
    0.48
     dictators
    0.48
     tokamaks
    0.47
     systèmes
    0.46
    یداری
    0.46
     emphatic
    0.46
    नियां
    0.46
    Act Density 0.001%

    No Known Activations