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

    Neuronpedia

    INDEX
    Explanations

    Polish 'temat'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     පිළ
    0.47
     आवृ
    0.47
     Ballroom
    0.47
     आपल्याला
    0.46
     දැන්
    0.46
     halaman
    0.45
    ▟
    0.45
    物品
    0.44
     Plate
    0.44
    umbling
    0.43
    POSITIVE LOGITS
    誒
    0.52
     homophobic
    0.50
    ო
    0.48
    ே
    0.48
     intolerable
    0.47
    ओं
    0.46
    ༧
    0.46
    ן
    0.46
    蜮
    0.45
     maximus
    0.45
    Act Density 0.000%

    No Known Activations