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

    Neuronpedia

    INDEX
    Explanations

    questions that start with "how."

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

    how introduces explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.56
    tagHelperRunner
    -0.52
     GenerationType
    -0.52
     تضيفلها
    -0.49
    principalColumn
    -0.47
     فريبيس
    -0.45
    HostException
    -0.45
    yntaxException
    -0.45
     OMITBAD
    -0.43
     BoxFit
    -0.43
    POSITIVE LOGITS
     utafitiHapana
    0.39
    cjonal
    0.38
    说过
    0.38
    TryDecodeAsNil
    0.38
     заявил
    0.38
    wär
    0.37
     réforme
    0.37
     ciento
    0.37
     aprobó
    0.36
     bahawa
    0.36
    Act Density 0.011%

    No Known Activations