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

    Neuronpedia

    INDEX
    Explanations

    DegreeReverse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شہری
    0.44
     cytoplasmic
    0.44
    الية
    0.43
    Ꮔ
    0.43
     cytosolic
    0.41
    луйста
    0.41
    POLICY
    0.40
     ciudadano
    0.40
     ভোক্তার
    0.40
    寯
    0.40
    POSITIVE LOGITS
     marker
    0.45
    Marker
    0.42
     markers
    0.37
     en
    0.37
     revers
    0.37
    itiers
    0.37
     ange
    0.36
     Marker
    0.36
     Markers
    0.36
    duke
    0.36
    Act Density 0.001%

    No Known Activations