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

    Neuronpedia

    INDEX
    Explanations

    phrasings related to staying on track or focus

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

    on *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.38
    CloseOperation
    -0.38
     Bud
    -0.34
     amus
    -0.34
     doInBackground
    -0.32
     выда
    -0.32
     everywhere
    -0.31
    strptime
    -0.30
     Proz
    -0.30
     Kauf
    -0.30
    POSITIVE LOGITS
    +#+#
    0.81
     الحره
    0.72
    makeConstraints
    0.69
    ConstraintMaker
    0.67
    0.64
    rungsseite
    0.61
     pinulongan
    0.60
     Италијани
    0.60
    moreland
    0.59
     cherchés
    0.58
    Act Density 0.019%

    No Known Activations