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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate direction or purpose

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

    bringing something to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.58
    ftagPool
    -0.54
    الدراسه
    -0.53
    industan
    -0.51
    SerializeField
    -0.51
    awtextra
    -0.50
     Excise
    -0.49
    buttonShape
    -0.48
    المناصب
    -0.48
    stdc
    -0.48
    POSITIVE LOGITS
    brought
    0.58
     Brought
    0.56
    bring
    0.54
     brought
    0.52
    Brought
    0.50
     Bring
    0.48
     brings
    0.47
     Bringing
    0.47
    Bringing
    0.47
    Bring
    0.46
    Act Density 0.019%

    No Known Activations