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

    Neuronpedia

    INDEX
    Explanations

    sentences containing prepositions and conjunctions showing a relationship between other words.

    oai_token-act-pair · gemini-2.0-flash

    references to existential concepts

    np_token-act-pair-logits · gpt-4o-mini

    "it"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     they
    -0.52
     उन्होंने
    -0.50
    ')[
    -0.49
    they
    -0.49
    стане
    -0.47
     caught
    -0.47
    hail
    -0.46
    uns
    -0.46
     of
    -0.45
     They
    -0.45
    POSITIVE LOGITS
     it
    1.17
     оно
    0.89
     nó
    0.85
    มัน
    0.81
     Оно
    0.80
    把它
    0.79
    GOTREF
    0.79
     esso
    0.75
    It
    0.74
    它
    0.72
    Act Density 13.212%

    No Known Activations