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

    Neuronpedia

    INDEX
    Explanations

    understanding topics of explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    0.55
    ρέ
    0.50
    рен
    0.48
    ارہ
    0.46
     dispatch
    0.46
     highways
    0.43
    কর্ত
    0.43
    ienna
    0.43
    ים
    0.42
    ל
    0.42
    POSITIVE LOGITS
    }).
    0.55
     dukkham
    0.55
     Journ
    0.52
     nasled
    0.48
    etri
    0.48
     lucru
    0.47
    quela
    0.47
     bölün
    0.46
    duğ
    0.44
     Instit
    0.44
    Act Density 0.001%

    No Known Activations