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

    Neuronpedia

    INDEX
    Explanations

    finding specific or related information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.49
    icial
    0.42
    umat
    0.39
    ও
    0.38
    ?
    0.38
     host
    0.37
    Avatar
    0.37
     आवाज
    0.36
    ВД
    0.36
     horizon
    0.35
    POSITIVE LOGITS
     माइट
    0.54
     കൊല്ല
    0.53
    για
    0.52
     می‌دهد
    0.51
     جلوگیری
    0.49
     brû
    0.48
    owały
    0.48
     می‌کند
    0.47
     ይሰ
    0.47
     dentées
    0.47
    Act Density 0.004%

    No Known Activations