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

    Neuronpedia

    INDEX
    Explanations

    emojis and jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल्लभ
    0.51
     Tattha
    0.50
     සා
    0.49
    。)
    0.47
    ('./
    0.46
    жд
    0.46
    Стро
    0.46
    ỏi
    0.45
     хотим
    0.44
    袍
    0.44
    POSITIVE LOGITS
     suis
    0.51
     HBO
    0.47
     minds
    0.47
     NBA
    0.44
     crítica
    0.44
     critica
    0.44
    চে
    0.44
     enemies
    0.43
     critical
    0.42
     layering
    0.41
    Act Density 0.002%

    No Known Activations