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

    Neuronpedia

    INDEX
    Explanations

    listing items or occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maupun
    0.52
     bunların
    0.50
     Rankings
    0.49
    angebot
    0.49
    ópolis
    0.49
     convierten
    0.49
     ataupun
    0.49
     itulah
    0.49
     जुगा
    0.49
     dejo
    0.48
    POSITIVE LOGITS
     acetate
    0.43
    feng
    0.43
    A
    0.41
     a
    0.41
    FullName
    0.41
    Name
    0.40
     surface
    0.39
     pillow
    0.39
     phong
    0.39
    풍
    0.38
    Act Density 0.002%

    No Known Activations