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

    Neuronpedia

    INDEX
    Explanations

    peer discovery and Kant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사망
    0.51
    ᖕ
    0.44
     hón
    0.42
     Sánchez
    0.41
    뿐
    0.40
     shakespeare
    0.40
    हदी
    0.39
    ᒻ
    0.39
    aktur
    0.39
    个月
    0.39
    POSITIVE LOGITS
     global
    0.44
    बु
    0.38
    丼
    0.38
    vised
    0.38
    global
    0.37
     वैश्विक
    0.36
     निकाय
    0.36
     navigate
    0.36
     endoscopy
    0.36
    SearchResult
    0.35
    Act Density 0.001%

    No Known Activations