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

    Neuronpedia

    INDEX
    Explanations

    reusable code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تجزی
    0.47
    ashmir
    0.47
    globalMap
    0.47
     ಪೊಲೀಸ
    0.46
     ઇ
    0.46
    ή
    0.45
     فی
    0.45
     ヒ
    0.44
     გამოყენ
    0.44
    揺
    0.44
    POSITIVE LOGITS
     meine
    0.58
     más
    0.52
     genero
    0.51
    sekten
    0.50
     contradict
    0.50
     ofere
    0.50
     end
    0.49
     recher
    0.49
     gera
    0.49
     peine
    0.48
    Act Density 0.001%

    No Known Activations