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

    Neuronpedia

    INDEX
    Explanations

    lines of code related to package imports in programming

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

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anschließend
    -0.39
     springfox
    -0.38
    ówczas
    -0.37
     inmediato
    -0.36
     antemano
    -0.36
    enderror
    -0.36
    AfterClass
    -0.36
     mandatario
    -0.36
     ddelweddau
    -0.35
     avanzado
    -0.34
    POSITIVE LOGITS
    import
    0.53
    trick
    0.49
     محفوظة
    0.48
    ImageContext
    0.47
     AssemblyTitle
    0.46
    <bos>
    0.46
    kry
    0.46
     Pristupljeno
    0.46
    freiheit
    0.45
    Agencia
    0.45
    Act Density 0.001%

    No Known Activations