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

    Neuronpedia

    INDEX
    Explanations

    ued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vish
    -0.07
     Gives
    -0.06
     Severity
    -0.06
     ~/
    -0.06
     Contractors
    -0.06
    .assertEqual
    -0.06
    SR
    -0.06
    /cs
    -0.06
     commissioners
    -0.06
    О
    -0.06
    POSITIVE LOGITS
    -themed
    0.07
    /////////////////////////////////////////////////////////////////////////////↵
    0.06
     nude
    0.06
     skyline
    0.06
     zvyš
    0.06
    ้้
    0.06
     هواپیم
    0.06
     hormone
    0.06
     ingres
    0.06
    0.06
    Act Density 0.001%

    No Known Activations