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

    Neuronpedia

    INDEX
    Explanations

    stings and bites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fin
    -0.07
    political
    -0.07
     Xin
    -0.07
    .sol
    -0.07
    VIN
    -0.06
     embodies
    -0.06
     runners
    -0.06
    frag
    -0.06
     sufficiently
    -0.06
     battles
    -0.06
    POSITIVE LOGITS
    ีช
    0.06
     dataSize
    0.06
     ек
    0.06
    атель
    0.06
     alcuni
    0.06
     deficit
    0.05
     Deserialize
    0.05
     tả
    0.05
    /frame
    0.05
    .Closed
    0.05
    Act Density 0.019%

    No Known Activations