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

    Neuronpedia

    INDEX
    Explanations

    existential needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     будь
    0.33
     possano
    0.29
     flowering
    0.29
     mooring
    0.29
     deteriorating
    0.28
     detailing
    0.28
     ritor
    0.28
     toning
    0.28
     counseling
    0.28
     eradication
    0.28
    POSITIVE LOGITS
     have
    0.44
     belong
    0.41
     deserve
    0.41
     know
    0.40
     want
    0.38
     need
    0.37
     गेट
    0.37
     exist
    0.35
     owe
    0.35
     understand
    0.35
    Act Density 0.053%

    No Known Activations