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

    Neuronpedia

    INDEX
    Explanations

    performing work and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     방법을
    0.39
     contents
    0.38
     relevance
    0.37
    urea
    0.37
     yönt
    0.36
    ificante
    0.35
     ability
    0.35
     queridos
    0.35
     реализу
    0.35
    の流れ
    0.35
    POSITIVE LOGITS
     intensive
    0.93
     groundwork
    0.90
     fieldwork
    0.87
     extensive
    0.84
     heavy
    0.83
     grunt
    0.83
    intensive
    0.80
    extensive
    0.75
     administrative
    0.74
     investigative
    0.74
    Act Density 0.080%

    No Known Activations