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

    Neuronpedia

    INDEX
    Explanations

    instances of ellipsis and continuation indicators in text

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

    Non-English words/tokens

    np_acts-logits-general · gemini-2.0-flash

    trail or pathway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cups
    -0.42
    MemoryWarning
    -0.41
    sharp
    -0.38
    bleed
    -0.38
     المب
    -0.37
    shoes
    -0.36
    OrWhiteSpace
    -0.36
    shoe
    -0.34
    withstanding
    -0.34
    GOTREF
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.60
     estekak
    0.59
    EndGlobalSection
    0.57
     HasFactory
    0.55
    /*
    0.55
    httphttps
    0.54
    verwijspagina
    0.52
     Италијани
    0.51
    /**
    0.51
     AssemblyTitle
    0.50
    Act Density 0.214%

    No Known Activations