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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or commands involving doing something

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

    do something or do so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.59
    CppMethod
    -0.57
    pushFollow
    -0.56
     defaultstate
    -0.54
    WaitGroup
    -0.52
     تضيفلها
    -0.52
    Personendaten
    -0.51
     combineReducers
    -0.50
     TextAppearance
    -0.50
     noqa
    -0.49
    POSITIVE LOGITS
    Doing
    0.47
    doing
    0.45
     exécu
    0.41
    قایناق‌لار
    0.40
     Doing
    0.38
     spéciaux
    0.37
     לעשות
    0.37
     estekak
    0.36
     uitvo
    0.36
    Aholisi
    0.36
    Act Density 0.041%

    No Known Activations