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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the beginning or transformation of something

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

    starting as X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.60
    MemoryWarning
    -0.50
    المشاركات
    -0.46
    MockMvc
    -0.46
     nahilalakip
    -0.45
     <<<<<<<<<<<<<<
    -0.43
    SourceChecksum
    -0.43
    stdc
    -0.41
     resourceCulture
    -0.41
    intios
    -0.41
    POSITIVE LOGITS
     semula
    0.63
     awalnya
    0.57
     originally
    0.52
     초기
    0.52
    Originally
    0.52
     initially
    0.51
     Originally
    0.50
    Initially
    0.50
     ursprünglichen
    0.49
     Initial
    0.48
    Act Density 0.014%

    No Known Activations