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

    Neuronpedia

    INDEX
    Explanations

    topics requiring expertise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以让
    0.47
     Edge
    0.40
     Body
    0.40
     Company
    0.39
     The
    0.39
    让
    0.39
     Simply
    0.38
    হাই
    0.38
     Señor
    0.38
     Getting
    0.38
    POSITIVE LOGITS
     często
    0.60
     často
    0.53
     ordinairement
    0.51
     nejsou
    0.51
     cenderung
    0.50
    requently
    0.49
     ofte
    0.48
     governs
    0.48
     janë
    0.47
     oftentimes
    0.47
    Act Density 0.004%

    No Known Activations