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

    Neuronpedia

    INDEX
    Explanations

    sardonic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     altura
    0.85
     setTasks
    0.82
     asociada
    0.80
    টা
    0.79
     quanta
    0.78
     importants
    0.76
     abut
    0.76
     wichtiger
    0.76
     instants
    0.75
     haies
    0.75
    POSITIVE LOGITS
     રીતે
    0.88
    𝐫
    0.82
    ように
    0.81
    𝐱
    0.77
    𝐲
    0.70
    0.70
    𝒞
    0.68
    lich
    0.68
     LDL
    0.68
    การ
    0.67
    Act Density 0.001%

    No Known Activations