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

    Neuronpedia

    INDEX
    Explanations

    understand you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibilidad
    0.39
     Sensitivity
    0.36
     privil
    0.36
     Naturally
    0.36
    FromName
    0.36
    LIFE
    0.36
    Sensitivity
    0.35
     curious
    0.34
    好奇
    0.34
    حده
    0.34
    POSITIVE LOGITS
    Howard
    0.45
     ARG
    0.42
    calaureate
    0.39
    榖
    0.37
    TGF
    0.36
     pendent
    0.36
    isons
    0.36
     tive
    0.35
     Hometown
    0.35
     ప్రే
    0.35
    Act Density 0.005%

    No Known Activations