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

    Neuronpedia

    INDEX
    Explanations

    domain and trademark search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.52
    us
    0.46
    '
    0.44
     précieux
    0.43
    ram
    0.43
    turns
    0.42
    urb
    0.41
     Frances
    0.41
    opf
    0.40
     bookings
    0.40
    POSITIVE LOGITS
     betta
    0.55
     매우
    0.51
    學
    0.51
     bandit
    0.48
     無
    0.47
     ಎಂದ
    0.47
     இஸ்
    0.46
     Reject
    0.46
     మీకు
    0.46
     reject
    0.46
    Act Density 0.001%

    No Known Activations