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

    Neuronpedia

    INDEX
    Explanations

    translate, relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     судеб
    0.50
     சொல்
    0.49
     سزا
    0.49
     تقد
    0.48
     സമ്പ
    0.47
     قوت
    0.47
     नायक
    0.46
     colère
    0.46
     héros
    0.45
     suprem
    0.44
    POSITIVE LOGITS
     of
    0.53
    ，
    0.51
    使用
    0.49
    www
    0.48
     interested
    0.48
    以
    0.47
    import
    0.46
    我
    0.46
     is
    0.45
     beverages
    0.45
    Act Density 0.003%

    No Known Activations