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

    Neuronpedia

    INDEX
    Explanations

    how questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गोष्टी
    0.36
    는지
    0.34
    랠
    0.30
     catégories
    0.29
    인지
    0.29
    messages
    0.28
    िक्त
    0.28
     সবকিছু
    0.28
     rzecz
    0.28
     коже
    0.28
    POSITIVE LOGITS
     accurate
    0.48
     worried
    0.42
     prevalent
    0.42
     close
    0.39
     long
    0.38
     reliable
    0.38
     Accurate
    0.38
     dangerous
    0.38
    accurate
    0.37
     profitable
    0.37
    Act Density 0.053%

    No Known Activations