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

    Neuronpedia

    INDEX
    Explanations

    specific items and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hauptsächlich
    0.48
     waarbij
    0.47
     különböző
    0.47
     berbagai
    0.46
     várias
    0.45
     bestimmten
    0.45
     quatro
    0.44
     çeşitli
    0.44
     bibli
    0.43
     kon
    0.43
    POSITIVE LOGITS
    יה
    0.50
    uy
    0.47
    ोर
    0.46
    oy
    0.46
    metaTag
    0.45
    신
    0.45
    ני
    0.44
    도
    0.44
    Ens
    0.44
    ור
    0.43
    Act Density 0.099%

    No Known Activations