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

    Neuronpedia

    INDEX
    Explanations

    location names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.84
    ########.
    -0.81
     ſhe
    -0.74
    ftagPool
    -0.68
     Monfieur
    -0.68
     Creighton
    -0.66
    клопе
    -0.65
    Jeografia
    -0.65
    UNGE
    -0.65
     myſelf
    -0.65
    POSITIVE LOGITS
    énario
    0.49
     Route
    0.44
     propOrder
    0.39
     AttributeSet
    0.35
    ResumeLayout
    0.33
     Way
    0.32
     disambiguazione
    0.31
     Rivers
    0.31
     Road
    0.30
     Riv
    0.30
    Act Density 0.001%

    No Known Activations