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

    Neuronpedia

    INDEX
    Explanations

    the word "home"

    oai_token-act-pair · gemini-2.0-flash

    home

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     שוליים
    -0.52
     ujednoznacz
    -0.46
    ◀
    -0.40
    btnCancel
    -0.40
    Hochspringen
    -0.40
     разве
    -0.39
    MockBean
    -0.39
    AndroidJUnit
    -0.39
     NUKAT
    -0.39
    oneofs
    -0.38
    POSITIVE LOGITS
    abestanden
    0.74
     UIColor
    0.63
    PreferredItem
    0.63
    unknownFields
    0.62
     برانيه
    0.62
    pegno
    0.60
    ]")]
    0.59
     Patro
    0.59
    ulaski
    0.59
     désolés
    0.58
    Act Density 0.177%

    No Known Activations