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

    Neuronpedia

    INDEX
    Explanations

    terms related to desirability and attractiveness of locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prime and desirable things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compositeur
    -0.43
     męski
    -0.39
     marié
    -0.38
     damski
    -0.36
    plastic
    -0.36
    FieldBuilder
    -0.36
    opcional
    -0.36
     blessé
    -0.35
    asional
    -0.35
     fonctionner
    -0.35
    POSITIVE LOGITS
     coveted
    0.54
     prestigious
    0.54
     desirable
    0.54
    IntoConstraints
    0.53
     kasarigan
    0.51
     East
    0.51
     waterfront
    0.47
    IsMutable
    0.47
     neighborhoods
    0.46
    లాలు
    0.46
    Act Density 0.002%

    No Known Activations