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

    Neuronpedia

    INDEX
    Explanations

    structured data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    プロ
    -0.08
    ະ
    -0.07
    기관
    -0.07
     ist
    -0.07
    /thread
    -0.07
     FileStream
    -0.07
    Spi
    -0.07
     informat
    -0.07
    HWND
    -0.07
     sharedApplication
    -0.07
    POSITIVE LOGITS
     fête
    0.07
    ’
    0.06
    |
    0.06
     gathered
    0.06
     Launcher
    0.06
    뵘
    0.06
    incible
    0.06
    balance
    0.06
    PILE
    0.06
     Aircraft
    0.06
    Act Density 0.033%

    No Known Activations