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

    Neuronpedia

    INDEX
    Explanations

    floor seats, space, sanitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    1.32
    c
    1.24
    是
    1.24
    ן
    1.19
    は
    1.15
    ين
    1.05
    ۔
    1.02
    не
    1.00
    دي
    0.96
    де
    0.95
    POSITIVE LOGITS
    0
    1.13
    '
    1.03
     pisos
    1.00
     floor
    0.95
     Floor
    0.93
     floors
    0.92
     preso
    0.90
    ip
    0.88
    很
    0.87
     transcoding
    0.85
    Act Density 0.004%

    No Known Activations