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

    Neuronpedia

    INDEX
    Explanations

    identify, rewrite, classify, answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financiar
    0.39
     গার্ডিয়ান
    0.38
     ferries
    0.37
     privés
    0.37
     prostit
    0.36
     justement
    0.34
     rifiuti
    0.34
     seafront
    0.34
     compartido
    0.34
     preocupa
    0.33
    POSITIVE LOGITS
    Identify
    0.43
     sentences
    0.42
     rewrite
    0.42
     rewritten
    0.42
     또는
    0.41
     Rewrite
    0.41
     identify
    0.41
    identify
    0.41
    निम्नलिखित
    0.40
     statements
    0.39
    Act Density 0.295%

    No Known Activations