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

    Neuronpedia

    INDEX
    Explanations

    'i' followed by specific words or code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.96
    nya
    0.80
    m
    0.77
    mike
    0.71
    lop
    0.71
    ls
    0.70
    م
    0.70
    यी
    0.69
    clothing
    0.69
    শাল
    0.67
    POSITIVE LOGITS
    verdad
    0.88
     мүмк
    0.86
    KON
    0.85
    ACC
    0.85
    ︠
    0.84
     dispuesto
    0.83
    ක්
    0.82
    Ast
    0.82
    Estas
    0.82
    workout
    0.82
    Act Density 0.178%

    No Known Activations