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

    Neuronpedia

    INDEX
    Explanations

    future possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kush
    -0.06
    どう
    -0.06
    _browser
    -0.06
    _revision
    -0.06
    _steps
    -0.06
    vara
    -0.05
    كة
    -0.05
    andWhere
    -0.05
    //----------------------------------------------------------------------------
    -0.05
    .Mock
    -0.05
    POSITIVE LOGITS
     toString
    0.07
     userInfo
    0.07
     SAS
    0.07
     Split
    0.07
    ackbar
    0.07
    LIC
    0.06
    .amazon
    0.06
     Surgical
    0.06
    شور
    0.06
    ijkl
    0.06
    Act Density 0.012%

    No Known Activations