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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating spatial or operational relationships in data contexts

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

    "of" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    of its purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SuppressMessage
    -0.44
    はじめに
    -0.41
    addCriterion
    -0.41
    +#+#
    -0.40
    httphttps
    -0.38
    {!!
    -0.37
    ReusableCell
    -0.35
    tagHelperRunner
    -0.35
    UnusedPrivate
    -0.35
     <<<<<<<<<<<<<<
    -0.34
    POSITIVE LOGITS
     itſelf
    0.60
     Beſ
    0.59
    ſelf
    0.58
     ſch
    0.54
     ſind
    0.54
     Eſ
    0.53
     ſtand
    0.53
     purpoſe
    0.52
     myſelf
    0.52
     Monfieur
    0.52
    Act Density 0.402%

    No Known Activations