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

    Neuronpedia

    INDEX
    Explanations

    instructional texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.55
    o
    0.46
    en
    0.40
    lı
    0.38
    é
    0.38
    group
    0.37
    ın
    0.37
    ir
    0.36
    r
    0.36
    eight
    0.35
    POSITIVE LOGITS
     VARIABLES
    0.32
     laboratorium
    0.32
     robotics
    0.31
     DON
    0.30
     computational
    0.30
     Robotics
    0.30
    ANK
    0.30
     kanker
    0.30
    穸
    0.30
     SCIENCE
    0.29
    Act Density 0.218%

    No Known Activations