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

    Neuronpedia

    INDEX
    Explanations

    September 2021 knowledge cutoff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Р
    0.84
    В
    0.84
    Когда
    0.80
    Д
    0.79
    П
    0.78
    Dieses
    0.78
    iscono
    0.77
     조정
    0.77
    У
    0.77
    व
    0.77
    POSITIVE LOGITS
     suitors
    0.88
     boleh
    0.82
     Summers
    0.79
    নাম
    0.78
    শিষ্ট
    0.77
     maksimum
    0.76
    స్తుంది
    0.75
     alamat
    0.75
     peonies
    0.74
     anthropology
    0.73
    Act Density 0.010%

    No Known Activations