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

    Neuronpedia

    INDEX
    Explanations

    terms related to damage and maintenance in appliances and systems

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

    damage or fragility

    np_acts-logits-general · gemini-2.0-flash

    vulnerability and damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    errHandler
    -0.45
    ismas
    -0.44
    ('.'
    -0.43
     förslag
    -0.42
    ConstraintMaker
    -0.42
     ý
    -0.41
     Viana
    -0.40
     proposta
    -0.40
    Requests
    -0.39
    æng
    -0.39
    POSITIVE LOGITS
     surfaces
    0.94
     internals
    0.91
     delicate
    0.90
     empfind
    0.89
     seams
    0.84
     fragile
    0.84
     sensitive
    0.83
     joints
    0.83
     interiors
    0.83
     integrity
    0.82
    Act Density 0.304%

    No Known Activations