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

    Neuronpedia

    INDEX
    Explanations

    guard statement or assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Null
    0.45
    Ped
    0.42
    }};
    0.42
     @
    0.41
    Paint
    0.41
    ped
    0.40
    Morph
    0.40
    Nathan
    0.40
    тол
    0.39
     ped
    0.39
    POSITIVE LOGITS
    guard
    0.49
     guarding
    0.46
     guarded
    0.46
     try
    0.45
     guard
    0.44
     Guardian
    0.43
     સિ
    0.43
     आए
    0.40
    UIApplication
    0.40
     GUARD
    0.38
    Act Density 0.011%

    No Known Activations