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

    Neuronpedia

    INDEX
    Explanations

    determiners followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    primarily
    0.61
    Conversely
    0.60
     continually
    0.57
     primarily
    0.54
     distinctly
    0.52
     utilizes
    0.52
     alternately
    0.52
    specifically
    0.52
    generally
    0.50
     proportionately
    0.50
    POSITIVE LOGITS
     ressources
    1.16
     planification
    1.16
     exercices
    1.11
     exercice
    1.09
     touristic
    1.09
     advices
    1.02
     reflexion
    0.98
     exemples
    0.95
     restauration
    0.95
     lenght
    0.92
    Act Density 0.015%

    No Known Activations