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

    Neuronpedia

    INDEX
    Explanations

    describing entities or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Related
    0.38
     Lann
    0.38
     disgr
    0.38
     связана
    0.37
     связан
    0.37
    懲
    0.36
     связанные
    0.36
     oyo
    0.35
    するように
    0.35
     приве
    0.35
    POSITIVE LOGITS
    ற்புத
    0.43
    Interact
    0.42
     سرح
    0.40
    Administrator
    0.39
     interact
    0.38
    correspond
    0.38
    administrator
    0.38
    ordin
    0.38
    true
    0.38
    natural
    0.37
    Act Density 0.000%

    No Known Activations