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

    Neuronpedia

    INDEX
    Explanations

    multilingual technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    active
    0.44
    damping
    0.43
    perception
    0.40
    reaction
    0.40
    Number
    0.40
    Type
    0.39
     articulation
    0.39
    Plas
    0.39
     sucrose
    0.39
    fl
    0.39
    POSITIVE LOGITS
     गोली
    0.48
     соответствует
    0.46
     філь
    0.46
    書法
    0.46
     AppMethodBeat
    0.45
    він
    0.45
     کشور
    0.44
     който
    0.44
     фильм
    0.43
     табли
    0.43
    Act Density 0.002%

    No Known Activations