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

    Neuronpedia

    INDEX
    Explanations

    instances of replacement or substitution

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

    taking someone's place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sarana
    -0.40
     paws
    -0.40
     rangka
    -0.38
     PyLong
    -0.38
     jurídico
    -0.38
    بوابة
    -0.37
     illustrationer
    -0.37
     jasa
    -0.37
     retrô
    -0.36
    Personendaten
    -0.36
    POSITIVE LOGITS
    MessageTagHelper
    0.55
     Replaced
    0.47
    PageRoute
    0.46
     surla
    0.45
    EndContext
    0.43
    Replaced
    0.43
    ChildScrollView
    0.43
     OnInit
    0.43
    +#+#
    0.43
    IsMutable
    0.42
    Act Density 0.022%

    No Known Activations