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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Want
    0.61
    Need
    0.57
     Need
    0.56
     möchten
    0.53
     Want
    0.52
     upang
    0.50
     lieber
    0.49
    NEED
    0.48
     необходимость
    0.48
    想要
    0.47
    POSITIVE LOGITS
     easily
    1.38
     facilement
    1.09
     comfortably
    1.09
     afford
    1.06
    easily
    1.03
     feas
    1.01
     conceivably
    1.00
     safely
    0.98
     facilmente
    0.96
     fácilmente
    0.94
    Act Density 0.599%

    No Known Activations