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

    Neuronpedia

    INDEX
    Explanations

    instructions and help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reward
    -0.07
    ,B
    -0.07
    Utilities
    -0.07
     Pearson
    -0.07
     Stokes
    -0.07
    -Day
    -0.06
     spender
    -0.06
     Internet
    -0.06
    -band
    -0.06
    -parent
    -0.06
    POSITIVE LOGITS
    yyvsp
    0.07
     ellipt
    0.07
    .createQuery
    0.07
    VK
    0.07
     conseguir
    0.07
     тверд
    0.06
    .placeholder
    0.06
    athed
    0.06
    呼ば
    0.06
    (car
    0.06
    Act Density 0.010%

    No Known Activations