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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or identifiers

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     femininas
    -0.43
     defaultstate
    -0.42
     Coimbra
    -0.41
     grecque
    -0.40
     dział
    -0.40
     fédé
    -0.39
     aufgestellt
    -0.39
     prosz
    -0.39
    ChrTalk
    -0.39
     Empfindung
    -0.38
    POSITIVE LOGITS
     مؤرشف
    1.08
     محفوظة
    0.88
     surla
    0.68
    jsii
    0.63
    GEBURTSDATUM
    0.59
     betweenstory
    0.54
     nakalista
    0.51
    rungsseite
    0.49
     CURIAM
    0.46
    \{\\
    0.45
    Act Density 0.000%

    No Known Activations