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

    Neuronpedia

    INDEX
    Explanations

    18/read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     racial
    -0.07
    _my
    -0.06
    ™
    -0.06
    анс
    -0.06
     pov
    -0.06
     widely
    -0.06
    _wallet
    -0.06
     tours
    -0.06
    िकट
    -0.06
    -social
    -0.06
    POSITIVE LOGITS
    getLocation
    0.07
     MainMenu
    0.07
    EMPLATE
    0.06
     FileReader
    0.06
    GetProcAddress
    0.06
    versed
    0.06
    .awtextra
    0.06
    SetBranchAddress
    0.06
    ErrorResponse
    0.06
     gauche
    0.06
    Act Density 0.002%

    No Known Activations