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

    Neuronpedia

    INDEX
    Explanations

    patterns of repetition or emphasis on specific phrases or structures throughout a document

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

    from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jegy
    -0.48
    EPC
    -0.44
     religione
    -0.42
     duquel
    -0.38
     hereby
    -0.37
     feminina
    -0.37
     jongen
    -0.37
    Hugo
    -0.36
     tecnica
    -0.36
    pcb
    -0.36
    POSITIVE LOGITS
    脚注の使い方
    0.69
     defaultstate
    0.62
    IndentedString
    0.62
    DeleteBehavior
    0.57
     AssemblyCulture
    0.56
     Roskov
    0.55
    complexContent
    0.54
    Bahkan
    0.52
    RegressionTest
    0.49
    Incluso
    0.49
    Act Density 0.027%

    No Known Activations