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

    Neuronpedia

    INDEX
    Explanations

    expressions of thought or contemplation

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

    opinion/assumption markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cand
    -0.45
    NS
    -0.42
     doInBackground
    -0.41
    manip
    -0.40
    松
    -0.39
    ceps
    -0.37
     manip
    -0.37
    نس
    -0.37
     laure
    -0.37
    Role
    -0.37
    POSITIVE LOGITS
    saraba
    0.61
    IntoConstraints
    0.57
    ########.
    0.54
    \{\\
    0.54
    RegressionTest
    0.53
    Personensuche
    0.52
    setHorizontal
    0.51
     pinulongan
    0.51
    الحياه
    0.49
    SpringRunner
    0.48
    Act Density 0.010%

    No Known Activations