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

    Neuronpedia

    INDEX
    Explanations

    git commands and code patches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    request
    0.49
     responding
    0.43
     proposal
    0.41
     🎉
    0.41
     petition
    0.41
    ల్లో
    0.40
    storm
    0.40
     पार्षद
    0.40
    Proposal
    0.40
     responders
    0.39
    POSITIVE LOGITS
    ObjectIndex
    0.41
     Tade
    0.40
     Index
    0.40
     શી
    0.40
    licts
    0.37
     index
    0.37
     dz
    0.37
     simpt
    0.36
     அனுப
    0.35
     Credits
    0.35
    Act Density 0.003%

    No Known Activations