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

    Neuronpedia

    INDEX
    Explanations

    phrases focusing on identity and self-referential concepts

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

    christened, crowned, named, becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haddad
    -0.38
    LEncoder
    -0.36
    fficacy
    -0.36
    jinal
    -0.36
    ymce
    -0.36
    eezy
    -0.35
     AppDelegate
    -0.35
    شار
    -0.35
    sbury
    -0.35
    PLUG
    -0.35
    POSITIVE LOGITS
    0.57
     blitt
    0.53
    Becoming
    0.52
    becoming
    0.50
     considerados
    0.49
     Becoming
    0.48
    ChildScrollView
    0.47
     kaarangay
    0.47
     Wikimedijinoj
    0.46
    extAlignment
    0.46
    Act Density 0.334%

    No Known Activations