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

    Neuronpedia

    INDEX
    Explanations

    references to recent developments and updates

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

    new developments and recent findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cshtml
    -0.45
    ReusableCell
    -0.44
    carter
    -0.43
     horseshoe
    -0.38
    NSON
    -0.38
     Schach
    -0.38
    <?
    -0.38
    YSIS
    -0.38
    瓮
    -0.37
     Secondo
    -0.36
    POSITIVE LOGITS
     updates
    0.53
     updating
    0.52
     uppdater
    0.50
     updated
    0.48
    updating
    0.48
     actualiza
    0.48
    nuevos
    0.47
     nuevos
    0.46
    最新的
    0.46
     actualización
    0.45
    Act Density 0.123%

    No Known Activations