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

    Neuronpedia

    INDEX
    Explanations

    expressions related to direction, correctness, and guidance in decision-making

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

    right direction or place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    లాలు
    -0.43
    CppMethod
    -0.38
     Paglinawan
    -0.36
     ioutil
    -0.34
    Erreferentziak
    -0.34
    🟤
    -0.33
    ırı
    -0.32
    /*!
    -0.32
     lith
    -0.31
    undra
    -0.31
    POSITIVE LOGITS
    yntaxException
    0.52
    IntoConstraints
    0.50
    addGap
    0.49
     Baumann
    0.49
    arangay
    0.48
    ikusbot
    0.48
    uidado
    0.47
     prioritizing
    0.46
     miniaturka
    0.45
    ViewFeatures
    0.45
    Act Density 0.012%

    No Known Activations