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

    Neuronpedia

    INDEX
    Explanations

    terms related to characteristics and parameters in scientific contexts

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

    Tokens followed by special characters like xe2x80x9

    np_acts-logits-general · gemini-2.0-flash

    quoted technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esetén
    -0.28
     raven
    -0.27
     tă
    -0.27
    çons
    -0.27
     kuta
    -0.26
    俗
    -0.26
     animo
    -0.25
     riuscito
    -0.25
    RefNanny
    -0.25
     Georges
    -0.25
    POSITIVE LOGITS
    UnusedPrivate
    0.63
    AsUp
    0.61
     zvuky
    0.58
     الحره
    0.58
     Италијани
    0.57
    ContentAsync
    0.57
    monary
    0.57
    KURZBESCHREIBUNG
    0.57
    rrggbb
    0.55
    énario
    0.55
    Act Density 0.561%

    No Known Activations