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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (UnityEngine
    -0.07
    .recipe
    -0.07
     Sass
    -0.07
    _accessible
    -0.07
    riters
    -0.06
     DataAccess
    -0.06
     Password
    -0.06
     에
    -0.06
     Ish
    -0.06
    ansible
    -0.06
    POSITIVE LOGITS
     lup
    0.08
    -long
    0.07
    빵
    0.07
    ilig
    0.07
    貅
    0.07
    归
    0.07
    关停
    0.07
    惠州
    0.07
     initiated
    0.06
     upbringing
    0.06
    Act Density 0.045%

    No Known Activations