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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing actions or emotional states

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

    Japanese polite verbs/verb endings

    np_acts-logits-general · gemini-2.0-flash

    Japanese verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いれば
    -0.51
    openqa
    -0.45
    sätzlich
    -0.45
     deton
    -0.45
    Ngo
    -0.44
    CommonModule
    -0.42
    TempData
    -0.41
    Lobby
    -0.41
    Salsa
    -0.41
    NAC
    -0.41
    POSITIVE LOGITS
    transQ
    0.63
    UnsafeEnabled
    0.54
    setVerticalGroup
    0.54
    RegistryLite
    0.52
     AssemblyCulture
    0.52
     propOrder
    0.52
     istore
    0.49
    ArgumentParser
    0.49
     ApiException
    0.47
    AndEndTag
    0.47
    Act Density 0.107%

    No Known Activations