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

    Neuronpedia

    INDEX
    Explanations

    NEW Object System

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ре
    0.64
    ров
    0.59
    ب
    0.58
    ס
    0.55
    op
    0.55
    bones
    0.54
    ال
    0.51
     limbs
    0.51
    적
    0.51
    ص
    0.50
    POSITIVE LOGITS
     социа
    0.63
     प्रतीत
    0.63
     sozial
    0.63
     Sozial
    0.62
     思い
    0.58
     Mall
    0.58
     dejamos
    0.55
    ক্ষণের
    0.54
     wodurch
    0.54
     Te
    0.54
    Act Density 0.012%

    No Known Activations