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

    Neuronpedia

    INDEX
    Explanations

    ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Connecticut
    -0.08
     bearbeiten
    -0.08
     NIH
    -0.07
    chester
    -0.07
    mitt
    -0.07
    IMUM
    -0.07
     Superb
    -0.07
     IV
    -0.07
     outright
    -0.07
    出租
    -0.07
    POSITIVE LOGITS
     solidarity
    0.11
     solidarité
    0.09
     solidaridad
    0.09
    กัน
    0.09
     camar
    0.08
     solidar
    0.08
     Spirit
    0.08
     강화
    0.08
     platelet
    0.08
     estre
    0.08
    Act Density 0.011%

    No Known Activations