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

    Neuronpedia

    INDEX
    Explanations

    intentional actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puedes
    1.35
     quieras
    1.30
     можете
    1.30
     엄마
    1.28
     alumnos
    1.26
     puede
    1.23
     quiera
    1.21
     може
    1.18
     peut
    1.17
    可以
    1.17
    POSITIVE LOGITS
     pursuing
    1.12
    timeslots
    1.07
     tenets
    1.03
    agements
    1.01
    futures
    1.01
    '%(
    1.01
    strptime
    0.99
     parip
    0.98
    ieuses
    0.98
    ilities
    0.97
    Act Density 0.101%

    No Known Activations