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

    Neuronpedia

    INDEX
    Explanations

    weighing the pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bereiche
    0.41
    ɭ
    0.39
    avir
    0.38
     evaluates
    0.38
     Evaluations
    0.37
    দর্শ
    0.37
     როგორ
    0.37
     Evaluación
    0.37
     perencanaan
    0.37
    au
    0.36
    POSITIVE LOGITS
     outweighed
    1.07
     outweigh
    1.02
     outweighs
    1.00
     weighed
    0.78
     inconvenience
    0.71
     inconven
    0.66
     negatives
    0.66
     weigh
    0.62
     gains
    0.61
     alternatives
    0.60
    Act Density 0.021%

    No Known Activations