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

    Neuronpedia

    INDEX
    Explanations

    model I have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     him
    1.14
    him
    0.91
     ним
    0.86
     his
    0.82
     его
    0.79
     ihn
    0.76
     lui
    0.76
     तिच्या
    0.75
     нём
    0.75
     அவன்
    0.74
    POSITIVE LOGITS
     requires
    0.76
     furnishes
    0.74
     richiede
    0.72
     qualifies
    0.71
     unveils
    0.69
     belongs
    0.68
     enhances
    0.68
     denotes
    0.67
     comfortably
    0.67
     operates
    0.66
    Act Density 0.000%

    No Known Activations