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

    Neuronpedia

    INDEX
    Explanations

    mess and spills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     숫
    0.42
    🈺
    0.39
     convertView
    0.39
    |");
    0.38
    ጾ
    0.38
    λον
    0.37
    暌
    0.37
     Phrase
    0.37
     विरो
    0.37
     восприя
    0.37
    POSITIVE LOGITS
     messy
    1.63
     spills
    1.61
     spill
    1.50
     mess
    1.41
     spilled
    1.41
     spilling
    1.37
     messes
    1.30
    mess
    1.28
     stains
    1.25
     staining
    1.16
    Act Density 0.025%

    No Known Activations