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

    Neuronpedia

    INDEX
    Explanations

    when clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সভাপত
    0.94
    média
    0.89
     sinnvoll
    0.87
     பெரும்பாலும்
    0.86
     აღმასრულ
    0.85
     대한
    0.85
     केली
    0.82
     일반적으로
    0.82
     veliko
    0.82
     समर्
    0.82
    POSITIVE LOGITS
     when
    1.00
     whenever
    0.93
    whenever
    0.90
    when
    0.86
     because
    0.85
     When
    0.81
     cuando
    0.81
     objects
    0.79
     যখন
    0.71
     quando
    0.71
    Act Density 0.310%

    No Known Activations