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

    Neuronpedia

    INDEX
    Explanations

    line numbers in python code

    oai_token-act-pair · gemini-2.0-flash

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Демографія
    -0.66
    น์
    -0.66
    zle
    -0.60
     grand
    -0.60
     her
    -0.60
     ru
    -0.59
    WithIOException
    -0.57
     ja
    -0.56
     led
    -0.55
     alt
    -0.55
    POSITIVE LOGITS
     rospy
    0.76
     mukana
    0.73
     nocturna
    0.73
     quadrature
    0.71
     Tenga
    0.69
    IsContent
    0.68
     handker
    0.68
     pregunto
    0.68
     Sarm
    0.68
     vallée
    0.68
    Act Density 0.617%

    No Known Activations