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

    Neuronpedia

    INDEX
    Explanations

    complex necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Scholar
    1.00
     Awakening
    0.99
     Improved
    0.98
    HAPPY
    0.95
     Poems
    0.95
     ब्राह्मण
    0.94
     wiser
    0.93
     Happy
    0.93
     Poem
    0.90
    happy
    0.90
    POSITIVE LOGITS
     densely
    1.45
    需要
    1.39
     nécess
    1.38
     interdependent
    1.33
    涉及到
    1.33
     volatile
    1.32
     potř
    1.31
     interrelated
    1.28
     complex
    1.28
     perishable
    1.28
    Act Density 1.163%

    No Known Activations