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

    Neuronpedia

    INDEX
    Explanations

    sequence and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    țile
    0.95
    фор
    0.92
    ave
    0.87
    ta
    0.84
    ă
    0.83
    es
    0.81
    tet
    0.79
    ัพท์
    0.77
    та
    0.77
     लगने
    0.76
    POSITIVE LOGITS
     functionals
    1.25
     វា
    1.24
     lacks
    1.23
     affixed
    1.23
    锞
    1.22
     compartments
    1.21
     sunglasses
    1.21
     townships
    1.20
     unterscheiden
    1.20
     tokamaks
    1.19
    Act Density 0.000%

    No Known Activations