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

    Neuronpedia

    INDEX
    Explanations

    numbers and prizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     millennials
    -0.08
    िषद
    -0.08
     drin
    -0.08
     deliber
    -0.08
     привыч
    -0.08
     rigs
    -0.08
     machine
    -0.07
    Machine
    -0.07
    Fresh
    -0.07
     fidd
    -0.07
    POSITIVE LOGITS
     rewarded
    0.10
    лава
    0.09
     Tier
    0.09
    /qu
    0.09
     rewarding
    0.08
    .reward
    0.08
     rescu
    0.08
     tess
    0.08
    Tier
    0.08
    等奖
    0.08
    Act Density 0.009%

    No Known Activations