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

    Neuronpedia

    INDEX
    Explanations

    WordPress PHP code hooks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sol
    0.43
     नारायण
    0.42
     fing
    0.42
    잤
    0.39
     Гор
    0.38
    Hors
    0.38
    Harm
    0.37
    Ỗ
    0.37
     bä
    0.37
     духо
    0.37
    POSITIVE LOGITS
     apply
    0.68
    wp
    0.64
     Applying
    0.64
    apply
    0.62
     esc
    0.61
     WP
    0.61
     applying
    0.57
     Apply
    0.56
     WC
    0.56
     wc
    0.55
    Act Density 0.007%

    No Known Activations