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

    Neuronpedia

    INDEX
    Explanations

    lobbying firms, members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하여
    0.43
    வராக
    0.39
    语
    0.39
    ২৪
    0.37
    كوم
    0.37
    矢
    0.36
     Livraison
    0.36
    하려고
    0.36
     करके
    0.36
    立場
    0.36
    POSITIVE LOGITS
    naive
    0.45
     islamic
    0.45
    Naive
    0.43
     summaries
    0.41
     essences
    0.39
     NMR
    0.38
     naive
    0.38
    essence
    0.38
    blk
    0.38
     SND
    0.38
    Act Density 0.000%

    No Known Activations