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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ock
    0.33
     Conserv
    0.32
    grand
    0.32
    ánicas
    0.32
    ಗಾರ
    0.31
    omat
    0.31
    ätten
    0.31
    enses
    0.30
    olic
    0.30
    craft
    0.30
    POSITIVE LOGITS
     Ni
    0.33
    တီ
    0.33
     नि
    0.31
    ǚ
    0.30
    вовано
    0.30
    咤
    0.29
     विधायक
    0.29
     وَ
    0.29
     gini
    0.28
    取締
    0.28
    Act Density 0.006%

    No Known Activations