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

    Neuronpedia

    INDEX
    Explanations

    remedies and soothing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insecurities
    0.38
     uncertainties
    0.38
    mern
    0.37
    osch
    0.37
    Undefined
    0.37
     Montague
    0.36
     instabilities
    0.36
     Lanka
    0.35
    埓
    0.35
    챌
    0.34
    POSITIVE LOGITS
     peppermint
    0.92
     drink
    0.73
    drink
    0.71
     massage
    0.69
     Magnesium
    0.68
     magnesium
    0.68
     massaging
    0.67
     Drink
    0.67
     Massage
    0.66
     sipping
    0.66
    Act Density 0.020%

    No Known Activations