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

    Neuronpedia

    INDEX
    Explanations

    Report for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੴ
    0.48
    م
    0.45
    瑋
    0.45
     inver
    0.45
    Ти
    0.44
    ц
    0.44
     다양
    0.44
     inwards
    0.43
    땅
    0.43
    Ձ
    0.42
    POSITIVE LOGITS
    simmons
    0.45
    orescence
    0.42
    ent
    0.41
     jama
    0.41
     सिराज
    0.41
    ologic
    0.40
    veless
    0.40
    মেজ
    0.39
    ores
    0.39
    考虑到
    0.39
    Act Density 0.001%

    No Known Activations