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

    Neuronpedia

    INDEX
    Explanations

    words related to behavior and actions done by people

    oai_token-act-pair · gemini-2.0-flash

    say ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     and
    -0.85
    NUMX
    -0.60
    !")
    -0.56
     gương
    -0.55
     
    -0.53
    .")
    -0.53
     ")[
    -0.52
    udadera
    -0.52
     bougies
    -0.52
    性和
    -0.51
    POSITIVE LOGITS
    ,
    0.92
     nakalista
    0.75
    InjectAttribute
    0.70
     تضيفلها
    0.65
    Personensuche
    0.64
    SharedDtor
    0.64
     jScrollPane
    0.60
     uintptr
    0.57
     Vikipedi
    0.56
    gnore
    0.56
    Act Density 1.672%

    No Known Activations