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

    Neuronpedia

    INDEX
    Explanations

    ordered and disorder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     наук
    -0.07
    *)"
    -0.07
    _sold
    -0.07
     plav
    -0.07
    Modal
    -0.07
     NPCs
    -0.07
     Nah
    -0.07
    Fullscreen
    -0.07
     llen
    -0.07
     ((__
    -0.06
    POSITIVE LOGITS
     Uber
    0.07
     Rocks
    0.06
    การส
    0.06
     Somerset
    0.06
    draft
    0.06
    akedirs
    0.06
     र
    0.06
     USC
    0.05
    UBLE
    0.05
    Tan
    0.05
    Act Density 0.007%

    No Known Activations