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

    Neuronpedia

    INDEX
    Explanations

    commands related to using a terminal and executing tasks

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

    typing or entering commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.69
    RegressionTest
    -0.64
    sizeCache
    -0.58
     queſta
    -0.50
    transQ
    -0.50
     MainAxisSize
    -0.50
    EDEFAULT
    -0.49
     tartalomajánló
    -0.48
     accountId
    -0.47
     Autorizaciones
    -0.47
    POSITIVE LOGITS
     Type
    0.36
    CommandType
    0.35
    cipta
    0.34
    łys
    0.34
    TYPED
    0.34
    zauber
    0.33
    CommandText
    0.32
     magic
    0.32
     PyTuple
    0.32
     halfway
    0.32
    Act Density 0.033%

    No Known Activations