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

    Neuronpedia

    INDEX
    Explanations

    deprecation and renaming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.64
     regency
    -0.60
     Reverso
    -0.60
     railroads
    -0.59
    ConstraintMaker
    -0.59
     railroad
    -0.56
    uxxxx
    -0.56
     magnets
    -0.54
     lapis
    -0.52
     skating
    -0.50
    POSITIVE LOGITS
    pulumi
    0.61
     MaterialApp
    0.58
     épais
    0.56
     Drittan
    0.54
    lenir
    0.53
     يتيمه
    0.53
     denominada
    0.52
     appelée
    0.51
     Named
    0.51
     LIVE
    0.51
    Act Density 0.006%

    No Known Activations