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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to deterioration and age

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

    states of disrepair and decay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vignon
    -0.39
    紆
    -0.35
    vician
    -0.35
    ķ
    -0.35
    MediaType
    -0.34
    melons
    -0.34
    SBATCH
    -0.33
    Usos
    -0.33
    ubung
    -0.33
    Gambas
    -0.33
    POSITIVE LOGITS
     dilapidated
    0.93
     shabby
    0.86
     rundown
    0.75
     dilap
    0.74
     tattered
    0.71
     battered
    0.68
     squal
    0.67
     derelict
    0.67
     decaying
    0.64
     dusty
    0.64
    Act Density 0.025%

    No Known Activations