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

    Neuronpedia

    INDEX
    Explanations

    AI guidelines enforced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evitando
    0.51
     vermeiden
    0.46
    ArchivePath
    0.46
     избе
    0.46
    避免
    0.45
     evitare
    0.44
     menghindari
    0.44
     предложить
    0.43
     avoiding
    0.42
     evitar
    0.42
    POSITIVE LOGITS
     enforced
    0.78
     imposed
    0.65
     inbuilt
    0.57
     deliberately
    0.55
     purposefully
    0.55
    imposed
    0.54
     ingrained
    0.54
     enshrined
    0.54
     designed
    0.54
     enforceable
    0.54
    Act Density 0.004%

    No Known Activations