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

    Neuronpedia

    INDEX
    Explanations

    code control flow statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Архі
    0.43
    𒊑
    0.42
    Roxy
    0.41
    ISPW
    0.40
    Deux
    0.39
     λειτουργ
    0.38
     גר
    0.38
     मेन
    0.38
     infrastrukt
    0.38
    Prix
    0.38
    POSITIVE LOGITS
    if
    0.61
    ↵
    0.50
    return
    0.49
    end
    0.48
     if
    0.48
     //
    0.48
     return
    0.47
     else
    0.45
    //
    0.43
              
    0.43
    Act Density 0.340%

    No Known Activations