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

    Neuronpedia

    INDEX
    Explanations

    "class"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    踪
    -0.09
     located
    -0.08
     Board
    -0.07
    结婚
    -0.07
    come
    -0.07
     ("
    -0.07
    ⽺
    -0.07
     mutual
    -0.07
    стан
    -0.07
     conclusions
    -0.07
    POSITIVE LOGITS
     grit
    0.07
     NRF
    0.07
    .Mod
    0.07
     usu
    0.07
     Friedman
    0.07
    optimizer
    0.07
     aftermarket
    0.07
    👌
    0.07
     Priority
    0.07
     taxa
    0.07
    Act Density 0.056%

    No Known Activations