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

    Neuronpedia

    INDEX
    Explanations

    excerpts/samples/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sexo
    -0.06
    -sama
    -0.06
     fld
    -0.06
    Seats
    -0.06
    	com
    -0.06
     เส
    -0.06
    -solving
    -0.06
    tier
    -0.06
    แส
    -0.06
     Національ
    -0.06
    POSITIVE LOGITS
     acknowledges
    0.07
    rious
    0.07
    034
    0.07
    _ENGINE
    0.06
    iciencies
    0.06
     Villa
    0.06
    Encoding
    0.06
     "../../
    0.06
     사람이
    0.06
    gün
    0.06
    Act Density 0.004%

    No Known Activations