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

    Neuronpedia

    INDEX
    Explanations

    Requirement Specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↓
    0.40
     Viitattu
    0.38
     <<
    0.36
    闻
    0.36
    ᕕ
    0.35
    ப்பின
    0.35
     inactivació
    0.35
     ↑
    0.35
    woł
    0.35
     disposto
    0.34
    POSITIVE LOGITS
     B
    0.53
     Brawl
    0.45
     Bc
    0.43
     BCH
    0.42
     BCA
    0.41
     BA
    0.40
     Buccaneers
    0.39
     Bd
    0.39
     BX
    0.38
     बी
    0.37
    Act Density 0.142%

    No Known Activations