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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of research or studies on a specific topic

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

    not examined comprehensively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.56
     TextAppearance
    -0.54
     referrerpolicy
    -0.51
    /**
    -0.49
     automatiques
    -0.45
    WriteAttribute
    -0.45
    vivencia
    -0.44
     biais
    -0.44
    osoba
    -0.44
    лтемелер
    -0.44
    POSITIVE LOGITS
    期刊论文
    0.41
     Lagi
    0.37
    이크
    0.35
     clef
    0.35
     GetEnumerator
    0.34
    真剣
    0.34
    cia
    0.34
    strict
    0.34
     contextLoads
    0.34
     Agung
    0.33
    Act Density 0.068%

    No Known Activations