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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .feed
    -0.07
     seizure
    -0.07
    一级
    -0.07
    decoder
    -0.06
     flock
    -0.06
     fontsize
    -0.06
     imagery
    -0.06
     sock
    -0.06
    چه
    -0.06
     cheeks
    -0.06
    POSITIVE LOGITS
    (double
    0.07
     christmas
    0.06
    慢
    0.06
     па
    0.06
     Dig
    0.06
    Subscribe
    0.06
     clandest
    0.06
     dig
    0.06
    ство
    0.06
     virtually
    0.06
    Act Density 0.013%

    No Known Activations