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

    Neuronpedia

    INDEX
    Explanations

    references to nicknames and affectionate terms

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

    nicknames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lizenz
    -0.35
     casada
    -0.34
     citas
    -0.34
     bể
    -0.32
    hoea
    -0.32
     pasado
    -0.32
     Förderung
    -0.32
    ceras
    -0.32
     croit
    -0.32
    probieren
    -0.31
    POSITIVE LOGITS
     nickname
    0.69
     Administrativna
    0.64
    下载附件
    0.61
    UnusedPrivate
    0.56
     nicknames
    0.56
    MigrationBuilder
    0.56
     colloquial
    0.54
    Personensuche
    0.53
     témoig
    0.52
     PopupWindow
    0.52
    Act Density 0.123%

    No Known Activations