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

    Neuronpedia

    INDEX
    Explanations

    embedded commands, sensory deprivation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synced
    0.68
     funcionalidades
    0.67
     uptick
    0.66
     onboarding
    0.65
     nuanced
    0.64
     underwhelming
    0.64
     esports
    0.64
     omnichannel
    0.64
     qubit
    0.63
     badass
    0.63
    POSITIVE LOGITS
     Attitudes
    0.58
     procedures
    0.57
     attitudes
    0.54
     Procedures
    0.54
     Problems
    0.52
     verbal
    0.52
     stimulated
    0.51
     emphasis
    0.50
     stimulating
    0.50
    verbal
    0.49
    Act Density 0.023%

    No Known Activations