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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing personal feelings and reflections

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

    many times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PLWABN
    -0.46
     للاسماء
    -0.45
    varlak
    -0.42
     tetrach
    -0.40
    Sectors
    -0.40
     régionales
    -0.40
    Verbindung
    -0.40
     nég
    -0.39
     dàng
    -0.39
     Cientí
    -0.39
    POSITIVE LOGITS
    RegressionTest
    0.57
    0.49
    DockStyle
    0.47
     Catawiki
    0.46
    __(/*!
    0.45
    RotationOrder
    0.43
    /**
    0.43
    //
    0.42
    eur
    0.41
     متعلقه
    0.40
    Act Density 0.081%

    No Known Activations