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

    Neuronpedia

    INDEX
    Explanations

    widely understood, feeling overwhelmed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    晚
    0.47
    치를
    0.46
     실패
    0.41
     কর্তৃপক্ষের
    0.40
    شت
    0.40
     sceptical
    0.40
     fáciles
    0.40
     secure
    0.39
    də
    0.39
    шло
    0.39
    POSITIVE LOGITS
    о
    0.51
    ,\"
    0.50
     Marissa
    0.50
     আঘাত
    0.48
    ,'
    0.48
     supporto
    0.48
    ubarb
    0.47
    iness
    0.47
    CONN
    0.46
     placa
    0.46
    Act Density 0.000%

    No Known Activations