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

    Neuronpedia

    INDEX
    Explanations

    potential ideas and futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acidosis
    0.95
     pathologies
    0.94
     capitalism
    0.91
     ailments
    0.90
     insecurities
    0.90
     toxicity
    0.90
     frauds
    0.88
     capitalismo
    0.88
     alcoholism
    0.88
     diseases
    0.88
    POSITIVE LOGITS
     melodic
    0.74
     decorative
    0.68
     floral
    0.68
     Blonde
    0.67
     charming
    0.67
     फूलों
    0.66
     puppet
    0.66
     choral
    0.65
     mermaid
    0.63
     virtual
    0.63
    Act Density 0.379%

    No Known Activations