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

    Neuronpedia

    INDEX
    Explanations

    phrases related to service quality and technician qualifications

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

    preceding adverbs or verbs

    np_acts-logits-general · gemini-2.0-flash

    technical sequences and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.76
    sizeCache
    -0.67
     allgemein
    -0.59
     unintended
    -0.59
    ConstraintMaker
    -0.56
     <=",
    -0.56
    ########.
    -0.53
     semej
    -0.52
     métallique
    -0.52
     spermato
    -0.52
    POSITIVE LOGITS
     proven
    0.78
    ousands
    0.74
    SPATH
    0.70
     our
    0.67
     carefully
    0.63
    edicated
    0.61
     validated
    0.61
     fully
    0.61
     dedicated
    0.60
     meticulously
    0.59
    Act Density 0.167%

    No Known Activations