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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases indicating a starting point or initial context

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

    in the first place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringBootTest
    -0.42
    ">//
    -0.41
     externi
    -0.40
     ब्रेकडाउन
    -0.40
    JspWriter
    -0.39
    ScopeManager
    -0.38
    Carriera
    -0.38
    出版年
    -0.37
    JsonFormat
    -0.36
    Ligações
    -0.36
    POSITIVE LOGITS
     First
    0.71
    First
    0.68
    первых
    0.66
     Initial
    0.66
     first
    0.64
     FIRST
    0.63
    first
    0.63
    Firstly
    0.63
    initial
    0.62
     Firstly
    0.61
    Act Density 0.004%

    No Known Activations