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

    Neuronpedia

    INDEX
    Explanations

    building infrastructure from core components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    venues
    0.41
    glicherweise
    0.40
    ighton
    0.39
     রহ
    0.37
    nhs
    0.37
    erView
    0.36
    wnież
    0.36
    തിന്
    0.36
    wk
    0.36
    బడి
    0.36
    POSITIVE LOGITS
     तलाक
    0.43
     mutable
    0.43
    Christina
    0.43
     '*',
    0.42
     Christina
    0.42
     stitches
    0.42
     सिंगर
    0.42
     Sev
    0.41
     Krist
    0.40
     pink
    0.38
    Act Density 0.000%

    No Known Activations