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

    Neuronpedia

    INDEX
    Explanations

    dwell in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thrott
    -0.08
     throttle
    -0.08
     grind
    -0.08
     conserving
    -0.07
     Production
    -0.07
    号码
    -0.07
     Race
    -0.07
     Conservation
    -0.07
     conserve
    -0.07
    Throttle
    -0.07
    POSITIVE LOGITS
     reside
    0.12
     resides
    0.12
     wohnen
    0.12
     residing
    0.11
    入住
    0.11
     residence
    0.11
     Aufent
    0.11
     habitation
    0.11
     resident
    0.10
     dwelling
    0.10
    Act Density 0.031%

    No Known Activations