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

    Neuronpedia

    INDEX
    Explanations

    reporting performance and proficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     społ
    0.55
    桎
    0.54
    ⌔
    0.53
    ેચ્છ
    0.51
    屒
    0.50
     medo
    0.50
    <unused220>
    0.50
    пенди
    0.49
    哌
    0.49
     alterações
    0.49
    POSITIVE LOGITS
      
    0.54
    mate
    0.50
    wellness
    0.50
    max
    0.48
     record
    0.48
    record
    0.48
    </td>
    0.47
     performance
    0.46
    int
    0.45
    attr
    0.44
    Act Density 0.001%

    No Known Activations