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

    Neuronpedia

    INDEX
    Explanations

    listing definitions or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     años
    0.47
     unisex
    0.47
    miles
    0.47
     multinationals
    0.46
     അടി
    0.46
     развитие
    0.46
     quarries
    0.46
     abuses
    0.44
    បន្ថែម
    0.43
     groves
    0.43
    POSITIVE LOGITS
    如果不
    0.42
    Asked
    0.41
    க்குற
    0.40
     J
    0.38
     그럼
    0.37
    طل
    0.37
    不要
    0.37
     其实
    0.37
    رسٹ
    0.36
     وهو
    0.36
    Act Density 0.000%

    No Known Activations