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

    Neuronpedia

    INDEX
    Explanations

    city

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impur
    -0.08
     Hahn
    -0.08
    Lim
    -0.08
     irre
    -0.08
     Lim
    -0.07
     Occasionally
    -0.07
    alaman
    -0.07
     piir
    -0.07
    ta
    -0.07
     apprenticeship
    -0.07
    POSITIVE LOGITS
     initiatives
    0.10
     envisioned
    0.09
     precinct
    0.09
     устойчив
    0.09
     구축
    0.09
     deployments
    0.08
     futuristic
    0.08
     infrastructures
    0.08
     enact
    0.08
     스마트
    0.08
    Act Density 0.011%

    No Known Activations