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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Игр
    -0.08
     flirting
    -0.07
    否則
    -0.07
    .Ch
    -0.07
    睾
    -0.07
    eree
    -0.07
     Sharks
    -0.07
     Genetic
    -0.07
    Tw
    -0.07
     Drugs
    -0.07
    POSITIVE LOGITS
    可以用
    0.07
    -${
    0.07
    ImageView
    0.07
    (random
    0.07
    <Text
    0.07
    רכיב
    0.07
    쮮
    0.06
     diğer
    0.06
    追随
    0.06
     belief
    0.06
    Act Density 0.020%

    No Known Activations