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

    Neuronpedia

    INDEX
    Explanations

    see or view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    0.51
    setAlignment
    0.39
     materials
    0.35
     prints
    0.35
     print
    0.34
     찾아
    0.34
    !”
    0.33
    ,
    0.33
    !”,
    0.33
    %!
    0.32
    POSITIVE LOGITS
    жаться
    0.53
    ounter
    0.53
    édi
    0.52
     قانونی
    0.52
    anées
    0.52
    办公室
    0.51
    ायक
    0.51
    ческа
    0.50
    cooking
    0.49
    uirre
    0.49
    Act Density 0.001%

    No Known Activations