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

    Neuronpedia

    INDEX
    Explanations

    Code / web frameworks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TÜ
    -0.07
     PIE
    -0.07
     одно
    -0.07
     troch
    -0.07
     RSVP
    -0.07
    洢
    -0.07
    _capacity
    -0.07
    _ne
    -0.06
    מאוחר
    -0.06
    퇀
    -0.06
    POSITIVE LOGITS
     silica
    0.07
     batches
    0.07
     settlers
    0.07
     Sims
    0.07
    hasil
    0.07
    Similar
    0.07
     warrants
    0.07
     Mét
    0.07
     aud
    0.07
    ि�
    0.06
    Act Density 0.008%

    No Known Activations