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

    Neuronpedia

    INDEX
    Explanations

    recipe ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =',
    0.69
    altezza
    0.68
     നിറ
    0.67
    Hons
    0.67
     ladr
    0.67
     cumprimento
    0.66
    /',
    0.66
    काला
    0.66
     nero
    0.66
     domes
    0.65
    POSITIVE LOGITS
    </h4>
    1.08
     Similar
    0.88
     Same
    0.81
     More
    0.81
    Similar
    0.80
    Same
    0.72
     Step
    0.72
     bulunan
    0.70
     ના
    0.70
     For
    0.70
    Act Density 0.033%

    No Known Activations