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

    Neuronpedia

    INDEX
    Explanations

    Short-form fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yaml
    -0.08
     Long
    -0.07
     Gaussian
    -0.06
    choice
    -0.06
     deviation
    -0.06
    Ada
    -0.06
    ifty
    -0.06
     Stability
    -0.06
    Critical
    -0.06
    $config
    -0.06
    POSITIVE LOGITS
    くらい
    0.07
    ὐ
    0.07
     Ré
    0.06
     совершенно
    0.06
    .XtraBars
    0.06
    ту
    0.06
    aptured
    0.06
     Scandinavian
    0.06
     ={↵
    0.06
     Blackjack
    0.06
    Act Density 0.091%

    No Known Activations