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

    Neuronpedia

    INDEX
    Explanations

    searching online for terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Preparation
    0.42
     £
    0.42
     Victorian
    0.41
     Tre
    0.40
     Screw
    0.38
    £
    0.38
    гот
    0.38
    oport
    0.38
    grep
    0.37
    俨
    0.37
    POSITIVE LOGITS
    WICK
    0.45
    WORTH
    0.38
     memudahkan
    0.38
    算法
    0.37
    STRING
    0.36
     ખે
    0.35
     familiale
    0.35
    Farmers
    0.35
     দেখুনঃ
    0.35
    Rules
    0.34
    Act Density 0.000%

    No Known Activations