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

    Neuronpedia

    INDEX
    Explanations

    Increased autistic traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ミ
    0.52
     zašt
    0.51
    Со
    0.50
    ソ
    0.50
    in
    0.50
    М
    0.49
    미
    0.49
    ῴ
    0.48
    К
    0.48
    Да
    0.47
    POSITIVE LOGITS
     Celebrating
    0.48
     Instagram
    0.47
     instagram
    0.45
    不怕
    0.45
     Banerjee
    0.45
     Histogram
    0.45
     positivos
    0.43
    matic
    0.42
     நிறுவனம்
    0.42
    🤓
    0.42
    Act Density 0.003%

    No Known Activations