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

    Neuronpedia

    INDEX
    Explanations

    otherwise or unable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    regardless
    0.40
     suht
    0.39
    িগুণ
    0.39
    Regardless
    0.39
    辎
    0.38
     esté
    0.38
    韮
    0.38
     фараз
    0.37
     needless
    0.37
     SAI
    0.37
    POSITIVE LOGITS
     otherwise
    0.73
    无法
    0.71
     insufficient
    0.70
     Otherwise
    0.69
    otherwise
    0.68
     unable
    0.67
     inadequate
    0.67
    Otherwise
    0.63
     Unable
    0.63
    無法
    0.62
    Act Density 0.489%

    No Known Activations