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

    Neuronpedia

    INDEX
    Explanations

    expresses ability or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    會在
    1.21
    ers
    1.14
    क
    1.10
    ging
    1.02
    ️
    1.01
    base
    1.01
    hese
    0.99
    身后
    0.96
     Didn
    0.95
    ing
    0.93
    POSITIVE LOGITS
     easily
    2.09
     Easily
    1.96
     fácilmente
    1.93
     इजीली
    1.92
     facilmente
    1.91
     afford
    1.70
     সহজেই
    1.61
     facilement
    1.55
     feas
    1.53
    easily
    1.51
    Act Density 2.001%

    No Known Activations