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

    Neuronpedia

    INDEX
    Explanations

    setting values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dury
    1.34
     Niro
    1.33
    ®.
    1.26
     Morn
    1.26
    accompan
    1.24
    ProductID
    1.22
    Forg
    1.22
    umbia
    1.18
     vina
    1.18
     copa
    1.18
    POSITIVE LOGITS
     set
    1.01
     Set
    0.99
    Set
    0.94
    set
    0.89
    Sets
    0.79
     Sets
    0.79
     sets
    0.78
    SET
    0.78
    鑲
    0.78
     SET
    0.75
    Act Density 0.141%

    No Known Activations