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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Crud
    -0.08
     Ord
    -0.07
    ✥
    -0.07
     crud
    -0.07
    ortic
    -0.07
     capacitor
    -0.07
     quartz
    -0.07
    𓂃
    -0.07
    Usuarios
    -0.07
    🍪
    -0.06
    POSITIVE LOGITS
     Roger
    0.08
    结构调整
    0.08
    찯
    0.07
     Sel
    0.07
    -manager
    0.07
    让她
    0.07
     Neh
    0.07
     effect
    0.07
     Challenges
    0.07
    年下半年
    0.07
    Act Density 0.001%

    No Known Activations