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

    Neuronpedia

    INDEX
    Explanations

    significance and impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वर्णन
    0.93
     helpful
    0.93
     helper
    0.90
     رہنے
    0.90
     guide
    0.89
     تساعد
    0.88
     guides
    0.88
     رہتا
    0.88
     descriptions
    0.87
     hilfreich
    0.85
    POSITIVE LOGITS
     symbolically
    1.34
     symbolism
    1.31
     symbolic
    1.31
     momentous
    1.30
     tantamount
    1.26
     precedent
    1.17
     disrespect
    1.16
     reaffirm
    1.15
     implications
    1.14
     significance
    1.11
    Act Density 0.965%

    No Known Activations